lunes, 30 de septiembre de 2024

AI simulation gives people a glimpse of their potential future self

Have you ever wanted to travel through time to see what your future self might be like? Now, thanks to the power of generative AI, you can.

Researchers from MIT and elsewhere created a system that enables users to have an online, text-based conversation with an AI-generated simulation of their potential future self.

Dubbed Future You, the system is aimed at helping young people improve their sense of future self-continuity, a psychological concept that describes how connected a person feels with their future self.

Research has shown that a stronger sense of future self-continuity can positively influence how people make long-term decisions, from one’s likelihood to contribute to financial savings to their focus on achieving academic success.

Future You utilizes a large language model that draws on information provided by the user to generate a relatable, virtual version of the individual at age 60. This simulated future self can answer questions about what someone’s life in the future could be like, as well as offer advice or insights on the path they could follow.

In an initial user study, the researchers found that after interacting with Future You for about half an hour, people reported decreased anxiety and felt a stronger sense of connection with their future selves.

“We don’t have a real time machine yet, but AI can be a type of virtual time machine. We can use this simulation to help people think more about the consequences of the choices they are making today,” says Pat Pataranutaporn, a recent Media Lab doctoral graduate who is actively developing a program to advance human-AI interaction research at MIT, and co-lead author of a paper on Future You.

Pataranutaporn is joined on the paper by co-lead authors Kavin Winson, a researcher at KASIKORN Labs; and Peggy Yin, a Harvard University undergraduate; as well as Auttasak Lapapirojn and Pichayoot Ouppaphan of KASIKORN Labs; and senior authors Monchai Lertsutthiwong, head of AI research at the KASIKORN Business-Technology Group; Pattie Maes, the Germeshausen Professor of Media, Arts, and Sciences and head of the Fluid Interfaces group at MIT, and Hal Hershfield, professor of marketing, behavioral decision making, and psychology at the University of California at Los Angeles. The research will be presented at the IEEE Conference on Frontiers in Education.

A realistic simulation

Studies about conceptualizing one’s future self go back to at least the 1960s. One early method aimed at improving future self-continuity had people write letters to their future selves. More recently, researchers utilized virtual reality goggles to help people visualize future versions of themselves.

But none of these methods were very interactive, limiting the impact they could have on a user.

With the advent of generative AI and large language models like ChatGPT, the researchers saw an opportunity to make a simulated future self that could discuss someone’s actual goals and aspirations during a normal conversation.

“The system makes the simulation very realistic. Future You is much more detailed than what a person could come up with by just imagining their future selves,” says Maes.

Users begin by answering a series of questions about their current lives, things that are important to them, and goals for the future.

The AI system uses this information to create what the researchers call “future self memories” which provide a backstory the model pulls from when interacting with the user.

For instance, the chatbot could talk about the highlights of someone’s future career or answer questions about how the user overcame a particular challenge. This is possible because ChatGPT has been trained on extensive data involving people talking about their lives, careers, and good and bad experiences.

The user engages with the tool in two ways: through introspection, when they consider their life and goals as they construct their future selves, and retrospection, when they contemplate whether the simulation reflects who they see themselves becoming, says Yin.

“You can imagine Future You as a story search space. You have a chance to hear how some of your experiences, which may still be emotionally charged for you now, could be metabolized over the course of time,” she says.

To help people visualize their future selves, the system generates an age-progressed photo of the user. The chatbot is also designed to provide vivid answers using phrases like “when I was your age,” so the simulation feels more like an actual future version of the individual.

The ability to take advice from an older version of oneself, rather than a generic AI, can have a stronger positive impact on a user contemplating an uncertain future, Hershfield says.

“The interactive, vivid components of the platform give the user an anchor point and take something that could result in anxious rumination and make it more concrete and productive,” he adds.

But that realism could backfire if the simulation moves in a negative direction. To prevent this, they ensure Future You cautions users that it shows only one potential version of their future self, and they have the agency to change their lives. Providing alternate answers to the questionnaire yields a totally different conversation.

“This is not a prophesy, but rather a possibility,” Pataranutaporn says.

Aiding self-development

To evaluate Future You, they conducted a user study with 344 individuals. Some users interacted with the system for 10-30 minutes, while others either interacted with a generic chatbot or only filled out surveys.

Participants who used Future You were able to build a closer relationship with their ideal future selves, based on a statistical analysis of their responses. These users also reported less anxiety about the future after their interactions. In addition, Future You users said the conversation felt sincere and that their values and beliefs seemed consistent in their simulated future identities.

“This work forges a new path by taking a well-established psychological technique to visualize times to come — an avatar of the future self — with cutting edge AI. This is exactly the type of work academics should be focusing on as technology to build virtual self models merges with large language models,” says Jeremy Bailenson, the Thomas More Storke Professor of Communication at Stanford University, who was not involved with this research.

Building off the results of this initial user study, the researchers continue to fine-tune the ways they establish context and prime users so they have conversations that help build a stronger sense of future self-continuity.

“We want to guide the user to talk about certain topics, rather than asking their future selves who the next president will be,” Pataranutaporn says.

They are also adding safeguards to prevent people from misusing the system. For instance, one could imagine a company creating a “future you” of a potential customer who achieves some great outcome in life because they purchased a particular product.

Moving forward, the researchers want to study specific applications of Future You, perhaps by enabling people to explore different careers or visualize how their everyday choices could impact climate change.

They are also gathering data from the Future You pilot to better understand how people use the system.

“We don’t want people to become dependent on this tool. Rather, we hope it is a meaningful experience that helps them see themselves and the world differently, and helps with self-development,” Maes says.



de MIT News https://ift.tt/2toh8mq

Aligning economic and regulatory frameworks for today’s nuclear reactor technology

Liam Hines ’22 didn't move to Sarasota, Florida, until high school, but he’s a Floridian through and through. He jokes that he’s even got a floral shirt, what he calls a “Florida formal,” for every occasion.

Which is why it broke his heart when toxic red algae used to devastate the Sunshine State’s coastline, including at his favorite beach, Caspersen. The outbreak made headline news during his high school years, with the blooms destroying marine wildlife and adversely impacting the state’s tourism-driven economy.

In Florida, Hines says, environmental awareness is pretty high because everyday citizens are being directly impacted by climate change. After all, it’s hard not to worry when beautiful white sand beaches are covered in dead fish. Ongoing concerns about the climate cemented Hines’ resolve to pick a career that would have a strong “positive environmental impact.” He chose nuclear, as he saw it as “a green, low-carbon-emissions energy source with a pretty straightforward path to implementation.”

Undergraduate studies at MIT

Knowing he wanted a career in the sciences, Hines applied and got accepted to MIT for undergraduate studies in fall 2018. An orientation program hosted by the Department of Nuclear Science and Engineering (NSE) sold him on the idea of pursuing the field. “The department is just a really tight-knit community, and that really appealed to me,” Hines says.

During his undergraduate years, Hines realized he needed a job to pay part of his bills. “Instead of answering calls at the dorm front desk or working in the dining halls, I decided I’m going to become a licensed nuclear operator onsite,” he says. “Reactor operations offer so much hands-on experience with real nuclear systems. It doesn’t hurt that it pays better.” Becoming a licensed nuclear reactor operator is hard work, however, involving a year-long training process studying maintenance, operations, and equipment oversight. A bonus: The job, supervising the MIT Nuclear Reactor Laboratory, taught him the fundamentals of nuclear physics and engineering.

Always interested in research, Hines got an early start by exploring the regulatory challenges of advanced fusion systems. There have been questions related to licensing requirements and the safety consequences of the onsite radionuclide inventory. Hines’ undergraduate research work involved studying precedent for such fusion facilities and comparing them to experimental facilities such as Princeton University’s Tokamak Fusion Test Reactor.

Doctoral focus on legal and regulatory frameworks

When scientists want to make technologies as safe as possible, they have to do two things in concert: First they evaluate the safety of the technology, and then make sure legal and regulatory structures take into account the evolution of these advanced technologies. Hines is taking such a two-pronged approach to his doctoral work on nuclear fission systems.

Under the guidance of Professor Koroush Shirvan, Hines is conducting systems modeling of various reactor cores that include graphite, and simulating operations under long time spans. He then studies radionuclide transport from low-level waste facilities — the consequences of offsite storage after 50 or 100 or even 10,000 years of storage. The work has to make sure to hit safety and engineering margins, but also tread a fine line. “You want to make sure you’re not over-engineering systems and adding undue cost, but also making sure to assess the unique hazards of these advanced technologies as accurately as possible,” Hines says.

On a parallel track, under Professor Haruko Wainwright’s advisement, Hines is applying the current science on radionuclide geochemistry to track radionuclide wastes and map their profile for hazards. One of the challenges fission reactors face is that existing low-level waste regulations were fine-tuned to old reactors. Regulations have not kept up: “Now that we have new technologies with new wastes, some of the hazards of the new waste are completely missed by existing standards,” Hines says. He is working to seal these gaps.

A philosophy-driven outlook

Hines is grateful for the dynamic learning environment at NSE. “A lot of the faculty have that go-getter attitude,” he points out, impressed by the entrepreneurial spirit on campus. “It’s made me confident to really tackle the things that I care about.”

An ethics class as an undergraduate made Hines realize there were discussions in class he could apply to the nuclear realm, especially when it came to teasing apart the implications of the technology — where the devices would be built and who they would serve. He eventually went on to double-major in NSE and philosophy.

The framework style of reading and reasoning involved in studying philosophy is particularly relevant in his current line of work, where he has to extract key points regarding nuclear regulatory issues. Much like philosophy discussions today that involve going over material that has been discussed for centuries and framing them through new perspectives, nuclear regulatory issues too need to take the long view.

“In philosophy, we have to insert ourselves into very large conversations. Similarly, in nuclear engineering, you have to understand how to take apart the discourse that’s most relevant to your research and frame it,” Hines says. This technique is especially necessary because most of the time the nuclear regulatory issues might seem like wading in the weeds of nitty-gritty technical matters, but they can have a huge impact on the public and public perception, Hines adds.

As for Florida, Hines visits every chance he can get. The red tide still surfaces but not as consistently as it once did. And since he started his job as a nuclear operator in his undergraduate days, Hines has progressed to senior reactor operator. This time around he gets to sign off on the checklists. “It’s much like when I was shift lead at Dunkin’ Donuts in high school,” Hines says, “everyone is kind of doing the same thing, but you get to be in charge for the afternoon.”



de MIT News https://ift.tt/yeFxjKE

AI pareidolia: Can machines spot faces in inanimate objects?

In 1994, Florida jewelry designer Diana Duyser discovered what she believed to be the Virgin Mary’s image in a grilled cheese sandwich, which she preserved and later auctioned for $28,000. But how much do we really understand about pareidolia, the phenomenon of seeing faces and patterns in objects when they aren’t really there? 

A new study from the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) delves into this phenomenon, introducing an extensive, human-labeled dataset of 5,000 pareidolic images, far surpassing previous collections. Using this dataset, the team discovered several surprising results about the differences between human and machine perception, and how the ability to see faces in a slice of toast might have saved your distant relatives’ lives.

“Face pareidolia has long fascinated psychologists, but it’s been largely unexplored in the computer vision community,” says Mark Hamilton, MIT PhD student in electrical engineering and computer science, CSAIL affiliate, and lead researcher on the work. “We wanted to create a resource that could help us understand how both humans and AI systems process these illusory faces.”

So what did all of these fake faces reveal? For one, AI models don’t seem to recognize pareidolic faces like we do. Surprisingly, the team found that it wasn’t until they trained algorithms to recognize animal faces that they became significantly better at detecting pareidolic faces. This unexpected connection hints at a possible evolutionary link between our ability to spot animal faces — crucial for survival — and our tendency to see faces in inanimate objects. “A result like this seems to suggest that pareidolia might not arise from human social behavior, but from something deeper: like quickly spotting a lurking tiger, or identifying which way a deer is looking so our primordial ancestors could hunt,” says Hamilton.

A row of five photos of animal faces atop five photos of inanimate objects that look like faces

Another intriguing discovery is what the researchers call the “Goldilocks Zone of Pareidolia,” a class of images where pareidolia is most likely to occur. “There’s a specific range of visual complexity where both humans and machines are most likely to perceive faces in non-face objects,” William T. Freeman, MIT professor of electrical engineering and computer science and principal investigator of the project says. “Too simple, and there’s not enough detail to form a face. Too complex, and it becomes visual noise.”

To uncover this, the team developed an equation that models how people and algorithms detect illusory faces.  When analyzing this equation, they found a clear “pareidolic peak” where the likelihood of seeing faces is highest, corresponding to images that have “just the right amount” of complexity. This predicted “Goldilocks zone” was then validated in tests with both real human subjects and AI face detection systems.

3 photos of clouds above 3 photos of a fruit tart. The left photo of each is “Too Simple” to perceive a face; the middle photo is “Just Right,” and the last photo is “Too Complex"

This new dataset, “Faces in Things,” dwarfs those of previous studies that typically used only 20-30 stimuli. This scale allowed the researchers to explore how state-of-the-art face detection algorithms behaved after fine-tuning on pareidolic faces, showing that not only could these algorithms be edited to detect these faces, but that they could also act as a silicon stand-in for our own brain, allowing the team to ask and answer questions about the origins of pareidolic face detection that are impossible to ask in humans. 

To build this dataset, the team curated approximately 20,000 candidate images from the LAION-5B dataset, which were then meticulously labeled and judged by human annotators. This process involved drawing bounding boxes around perceived faces and answering detailed questions about each face, such as the perceived emotion, age, and whether the face was accidental or intentional. “Gathering and annotating thousands of images was a monumental task,” says Hamilton. “Much of the dataset owes its existence to my mom,” a retired banker, “who spent countless hours lovingly labeling images for our analysis.”

The study also has potential applications in improving face detection systems by reducing false positives, which could have implications for fields like self-driving cars, human-computer interaction, and robotics. The dataset and models could also help areas like product design, where understanding and controlling pareidolia could create better products. “Imagine being able to automatically tweak the design of a car or a child’s toy so it looks friendlier, or ensuring a medical device doesn’t inadvertently appear threatening,” says Hamilton.

“It’s fascinating how humans instinctively interpret inanimate objects with human-like traits. For instance, when you glance at an electrical socket, you might immediately envision it singing, and you can even imagine how it would ‘move its lips.’ Algorithms, however, don’t naturally recognize these cartoonish faces in the same way we do,” says Hamilton. “This raises intriguing questions: What accounts for this difference between human perception and algorithmic interpretation? Is pareidolia beneficial or detrimental? Why don’t algorithms experience this effect as we do? These questions sparked our investigation, as this classic psychological phenomenon in humans had not been thoroughly explored in algorithms.”

As the researchers prepare to share their dataset with the scientific community, they’re already looking ahead. Future work may involve training vision-language models to understand and describe pareidolic faces, potentially leading to AI systems that can engage with visual stimuli in more human-like ways.

“This is a delightful paper! It is fun to read and it makes me think. Hamilton et al. propose a tantalizing question: Why do we see faces in things?” says Pietro Perona, the Allen E. Puckett Professor of Electrical Engineering at Caltech, who was not involved in the work. “As they point out, learning from examples, including animal faces, goes only half-way to explaining the phenomenon. I bet that thinking about this question will teach us something important about how our visual system generalizes beyond the training it receives through life.”

Hamilton and Freeman’s co-authors include Simon Stent, staff research scientist at the Toyota Research Institute; Ruth Rosenholtz, principal research scientist in the Department of Brain and Cognitive Sciences, NVIDIA research scientist, and former CSAIL member; and CSAIL affiliates postdoc Vasha DuTell, Anne Harrington MEng ’23, and Research Scientist Jennifer Corbett. Their work was supported, in part, by the National Science Foundation and the CSAIL MEnTorEd Opportunities in Research (METEOR) Fellowship, while being sponsored by the United States Air Force Research Laboratory and the United States Air Force Artificial Intelligence Accelerator. The MIT SuperCloud and Lincoln Laboratory Supercomputing Center provided HPC resources for the researchers’ results.

This work is being presented this week at the European Conference on Computer Vision.



de MIT News https://ift.tt/YZJkdq8

domingo, 29 de septiembre de 2024

Where flood policy helps most — and where it could do more

Flooding, including the devastation caused recently by Hurricane Helene, is responsible for $5 billion in annual damages in the U.S. That’s more than any other type of weather-related extreme event.

To address the problem, the federal government instituted a program in 1990 that helps reduce flood insurance costs in communities enacting measures to better handle flooding. If, say, a town preserves open space as a buffer against coastal flooding, or develops better stormwater management, area policy owners get discounts on their premiums. Studies show the program works well: It has reduced overall flood damage in participating communities.

However, a new study led by an MIT researcher shows that the effects of the program differ greatly from place to place. For instance, higher-population communities, which likely have more means to introduce flood defenses, benefit more than smaller communities, to the tune of about $4,000 per insured household.

“When we evaluate it, the effects of the same policy vary widely among different types of communities,” says study co-author Lidia Cano Pecharromán, a PhD candidate in MIT’s Department of Urban Studies and Planning.

Referring to climate and environmental justice concerns, she adds: “It’s important to understand not just if a policy is effective, but who is benefitting, so that we can make necessary adjustments and reach all the targets we want to reach.”

The paper, “Exposing Disparities in Flood Adaptation for Equitable Future Interventions in the USA,” is published today in Nature Communications. The authors are Cano Pecharromán and ChangHoon Hahn, an associate research scholar at Princeton University.

Able to afford help

The program in question was developed by the Federal Emergency Management Agency (FEMA), which has a division, the Flood Insurance Mitigation Administration, focusing on this issue. In 1990, FEMA initiated the National Flood Insurance Program’s Community Rating System, which incentivizes communities to enact measures that help prevent or reduce flooding.

Communities can engage in a broad set of related activities, including floodplain mapping, preservation of open spaces, stormwater management activities, creating flood warning systems, or even developing public information and participation programs. In exchange, area residents receive a discount on their flood insurance premium rates.

To conduct the study, the researchers examined 2.5 million flood insurance claims filed with FEMA since then. They also examined U.S. Census Bureau data to analyze demographic and economic data about communities, and incorporated flood risk data from the First Street Foundation.

By comparing over 1,500 communities in the FEMA program, the researchers were able to quantify its different relative effects — depending on community characteristics such as population, race, income or flood risk. For instance, higher-income communities seem better able to make more flood-control and mitigation investments, earning better FEMA ratings and, ultimately, enacting more effective measures.

“You see some positive effects for low-income communities, but as the risks go up, these disappear, while only high-income communities continue seeing these positive effects,” says Cano Pecharromán. “They are likely able to afford measures that handle a higher risk indices for flooding.”

Similarly, the researchers found, communities with higher overall levels of education fare better from the flood-insurance program, with about $2,000 more in savings per individual policy than communities with lower levels of education. One way or another, communities with more assets in the first place — size, wealth, education — are better able to deploy or hire the civic and technical expertise necessary to enact more best practices against flood damage.

And even among lower-income communities in the program, communities with less population diversity see greater effectiveness from their flood program activities, realizing a gain of about $6,000 per household compared to communities where racial and ethnic minorities are predominant.

“These are substantial effects, and we should consider these things when making decisions and reviewing if our climate adaptation policies work,” Cano Pecharromán says.

An even larger number of communities is not in the FEMA program at all. The study identified 14,729 unique U.S. communities with flood issues. Many of those are likely lacking the capacity to engage on flooding issues the way even the lower-ranked communities within the FEMA program have at least taken some action so far.

“If we are able to consider all the communities that are not in the program because they can’t afford to do the basics, we would likely see that the effects are even larger among different communities,” Cano Pecharromán says.

Getting communities started

To make the program more effective for more people, Cano Pecharromán suggests that the federal government should consider how to help communities enact flood-control and mitigation measures in the first place.

“When we set out these kinds of policies, we need to consider how certain types of communities might need help with implementation,” she says.

Methodologically, the researchers arrived at their conclusions using an advanced statistical approach that Hahn, who is an astrophysicist by training, has applied to the study of dark energy and galaxies. Instead of finding one “average treatment effect” of the FEMA program across all participating communities, they quantified the program’s impact while subdividing the set of participating set of communities according to their characteristics.

“We are able to calculate the causal effect of [the program], not as an average, which can hide these inequalities, but at every given level of the specific characteristic of communities we’re looking at, different levels of income, different levels of education, and more,” Cano Pecharromán says.

Government officials have seen Cano Pecharromán present the preliminary findings at meetings, and expressed interest in the results. Currently, she is also working on a follow-up study, which aims to pinpoint which types of local flood-mitigation programs provide the biggest benefits for local communities.

Support for the research was provided, in part, by the La Caixa Foundation, the MIT Martin Family Society of Fellows for Sustainability, and the AI Accelerator program of the Schmidt Futures Foundation.



de MIT News https://ift.tt/LMF2UEw

Helping robots zero in on the objects that matter

Imagine having to straighten up a messy kitchen, starting with a counter littered with sauce packets. If your goal is to wipe the counter clean, you might sweep up the packets as a group. If, however, you wanted to first pick out the mustard packets before throwing the rest away, you would sort more discriminately, by sauce type. And if, among the mustards, you had a hankering for Grey Poupon, finding this specific brand would entail a more careful search.

MIT engineers have developed a method that enables robots to make similarly intuitive, task-relevant decisions.

The team’s new approach, named Clio, enables a robot to identify the parts of a scene that matter, given the tasks at hand. With Clio, a robot takes in a list of tasks described in natural language and, based on those tasks, it then determines the level of granularity required to interpret its surroundings and “remember” only the parts of a scene that are relevant.

In real experiments ranging from a cluttered cubicle to a five-story building on MIT’s campus, the team used Clio to automatically segment a scene at different levels of granularity, based on a set of tasks specified in natural-language prompts such as “move rack of magazines” and “get first aid kit.”

The team also ran Clio in real-time on a quadruped robot. As the robot explored an office building, Clio identified and mapped only those parts of the scene that related to the robot’s tasks (such as retrieving a dog toy while ignoring piles of office supplies), allowing the robot to grasp the objects of interest.

Clio is named after the Greek muse of history, for its ability to identify and remember only the elements that matter for a given task. The researchers envision that Clio would be useful in many situations and environments in which a robot would have to quickly survey and make sense of its surroundings in the context of its given task.

“Search and rescue is the motivating application for this work, but Clio can also power domestic robots and robots working on a factory floor alongside humans,” says Luca Carlone, associate professor in MIT’s Department of Aeronautics and Astronautics (AeroAstro), principal investigator in the Laboratory for Information and Decision Systems (LIDS), and director of the MIT SPARK Laboratory. “It’s really about helping the robot understand the environment and what it has to remember in order to carry out its mission.”

The team details their results in a study appearing today in the journal Robotics and Automation Letters. Carlone’s co-authors include members of the SPARK Lab: Dominic Maggio, Yun Chang, Nathan Hughes, and Lukas Schmid; and members of MIT Lincoln Laboratory: Matthew Trang, Dan Griffith, Carlyn Dougherty, and Eric Cristofalo.

Open fields

Huge advances in the fields of computer vision and natural language processing have enabled robots to identify objects in their surroundings. But until recently, robots were only able to do so in “closed-set” scenarios, where they are programmed to work in a carefully curated and controlled environment, with a finite number of objects that the robot has been pretrained to recognize.

In recent years, researchers have taken a more “open” approach to enable robots to recognize objects in more realistic settings. In the field of open-set recognition, researchers have leveraged deep-learning tools to build neural networks that can process billions of images from the internet, along with each image’s associated text (such as a friend’s Facebook picture of a dog, captioned “Meet my new puppy!”).

From millions of image-text pairs, a neural network learns from, then identifies, those segments in a scene that are characteristic of certain terms, such as a dog. A robot can then apply that neural network to spot a dog in a totally new scene.

But a challenge still remains as to how to parse a scene in a useful way that is relevant for a particular task.

“Typical methods will pick some arbitrary, fixed level of granularity for determining how to fuse segments of a scene into what you can consider as one ‘object,’” Maggio says. “However, the granularity of what you call an ‘object’ is actually related to what the robot has to do. If that granularity is fixed without considering the tasks, then the robot may end up with a map that isn’t useful for its tasks.”

Information bottleneck

With Clio, the MIT team aimed to enable robots to interpret their surroundings with a level of granularity that can be automatically tuned to the tasks at hand.

For instance, given a task of moving a stack of books to a shelf, the robot should be able to  determine that the entire stack of books is the task-relevant object. Likewise, if the task were to move only the green book from the rest of the stack, the robot should distinguish the green book as a single target object and disregard the rest of the scene — including the other books in the stack.

The team’s approach combines state-of-the-art computer vision and large language models comprising neural networks that make connections among millions of open-source images and semantic text. They also incorporate mapping tools that automatically split an image into many small segments, which can be fed into the neural network to determine if certain segments are semantically similar. The researchers then leverage an idea from classic information theory called the “information bottleneck,” which they use to compress a number of image segments in a way that picks out and stores segments that are semantically most relevant to a given task.

“For example, say there is a pile of books in the scene and my task is just to get the green book. In that case we push all this information about the scene through this bottleneck and end up with a cluster of segments that represent the green book,” Maggio explains. “All the other segments that are not relevant just get grouped in a cluster which we can simply remove. And we’re left with an object at the right granularity that is needed to support my task.”

The researchers demonstrated Clio in different real-world environments.

“What we thought would be a really no-nonsense experiment would be to run Clio in my apartment, where I didn’t do any cleaning beforehand,” Maggio says.

The team drew up a list of natural-language tasks, such as “move pile of clothes” and then applied Clio to images of Maggio’s cluttered apartment. In these cases, Clio was able to quickly segment scenes of the apartment and feed the segments through the Information Bottleneck algorithm to identify those segments that made up the pile of clothes.

They also ran Clio on Boston Dynamic’s quadruped robot, Spot. They gave the robot a list of tasks to complete, and as the robot explored and mapped the inside of an office building, Clio ran in real-time on an on-board computer mounted to Spot, to pick out segments in the mapped scenes that visually relate to the given task. The method generated an overlaying map showing just the target objects, which the robot then used to approach the identified objects and physically complete the task.

“Running Clio in real-time was a big accomplishment for the team,” Maggio says. “A lot of prior work can take several hours to run.”

Going forward, the team plans to adapt Clio to be able to handle higher-level tasks and build upon recent advances in photorealistic visual scene representations.

“We’re still giving Clio tasks that are somewhat specific, like ‘find deck of cards,’” Maggio says. “For search and rescue, you need to give it more high-level tasks, like ‘find survivors,’ or ‘get power back on.’ So, we want to get to a more human-level understanding of how to accomplish more complex tasks.”

This research was supported, in part, by the U.S. National Science Foundation, the Swiss National Science Foundation, MIT Lincoln Laboratory, the U.S. Office of Naval Research, and the U.S. Army Research Lab Distributed and Collaborative Intelligent Systems and Technology Collaborative Research Alliance.



de MIT News https://ift.tt/uQrSL9i

viernes, 27 de septiembre de 2024

MIT launches new Music Technology and Computation Graduate Program

A new, multidisciplinary MIT graduate program in music technology and computation will feature faculty, labs, and curricula from across the Institute.

The program is a collaboration between the Music and Theater Arts Section in the School of Humanities, Arts, and Social Sciences (SHASS); Department of Electrical Engineering and Computer Science (EECS) in the School of Engineering; and the MIT Schwarzman College of Computing.

“The launch of a new graduate program in music technology strikes me as both a necessary and a provocative gesture — an important leap in an era being rapidly redefined by exponential growth in computation, artificial intelligence, and human-computer interactions of every conceivable kind,” says Jay Scheib,​​ head of the MIT Music and Theater Arts Section and the Class of 1949 Professor.

“Music plays an elegant role at the fore of a remarkable convergence of art and technology,” adds Scheib. “It’s the right time to launch this program and if not at MIT, then where?”

MIT’s practitioners define music technology as the field of scientific inquiry where they study, discover, and develop new computational approaches to music that include music information retrieval; artificial intelligence; machine learning; generative algorithms; interaction and performance systems; digital instrument design; conceptual and perceptual modeling of music; acoustics; audio signal processing; and software development for creative expression and music applications.

Eran Egozy, professor of the practice in music technology and one of the program leads, says MIT’s focus is technical research in music technology that always centers the humanistic and artistic aspects of making music.

“There are so many MIT students who are fabulous musicians,” says Egozy. “We'll approach music technology as computer scientists, mathematicians, and musicians.”

With the launch of this new program — an offering alongside those available in MIT’s Media Lab and elsewhere — Egozy sees MIT becoming the obvious destination for students interested in music and computation study, preparing high-impact graduates for roles in academia and industry, while also helping mold creative, big-picture thinkers who can tackle large challenges.

Investigating big ideas

The program will encompass two master’s degrees and a PhD:

  • The Master of Science (MS) is a two-semester, thesis-based program available only to MIT undergraduates. One semester of fellowship is automatically awarded to all admitted students. The first class will enroll in fall 2025.
  • The Master of Applied Science (MAS) is a two-semester, coursework-based program available to all students. One semester of fellowship funding is automatically awarded to all admitted students. Applications for this program will open in fall 2025.
  • The PhD program is available to all students, who would apply to MIT’s School of Engineering.

Anna Huang, a new MIT assistant professor who holds a shared faculty position between the MIT Music and Theater Arts Section and the MIT Schwarzman College of Computing, is collaborating with Egozy to develop and launch the program. Huang arrived at MIT this fall after spending eight years with Magenta at Google Brain and DeepMind, spearheading efforts in generative modeling, reinforcement learning, and human-computer interaction to support human-AI partnerships in music-making.

“As a composer turned AI researcher who specializes in generative music technology, my long-term goal is to develop AI systems that can shed new light on how we understand, learn, and create music, and to learn from interactions between musicians in order to transform how we approach human-AI collaboration,” says Huang. “This new program will let us further investigate how musical applications can illuminate problems in understanding neural networks, for example.”

MIT’s new Edward and Joyce Linde Music Building, featuring enhanced music technology spaces, will also help transform music education with versatile performance venues and optimized rehearsal facilities.

A natural home for music technology

MIT’s world-class, top-ranked engineering program, combined with its focus on computation and its conservatory-level music education offerings, makes the Institute a natural home for the continued expansion of music technology education.

The collaborative nature of the new program is the latest example of interdisciplinary work happening across the Institute.

“I am thrilled that the School of Engineering is partnering with the MIT Music and Theater Arts Section on this important initiative, which represents the convergence of various engineering areas — such as AI and design — with music,” says Anantha Chandrakasan, dean of the School of Engineering, chief innovation and strategy officer, and the Vannevar Bush Professor of EECS. “I can’t wait to see the innovative projects the students will create and how they will drive this new field forward.”

“Everyone on campus knows that MIT is a great place to do music. But I want people to come to MIT because of what we do in music,” says Agustin Rayo, the Kenan Sahin Dean of SHASS. “This outstanding collaboration with the Schwarzman College of Computing and the School of Engineering will make that dream a reality, by bringing together the world’s best engineers with our extraordinary musicians to create the next generation of music technologies.”

“The new master’s program offers students an unparalleled opportunity to explore the intersection of music and technology,” says Daniel Huttenlocher, dean of the MIT Schwarzman College of Computing and the Henry Ellis Warren Professor of EECS. “It equips them with a deep understanding of this confluence, preparing them to advance new approaches to computational models of music and be at the forefront of an evolving area.” 



de MIT News https://ift.tt/chICapl

miércoles, 25 de septiembre de 2024

New security protocol shields data from attackers during cloud-based computation

Deep-learning models are being used in many fields, from health care diagnostics to financial forecasting. However, these models are so computationally intensive that they require the use of powerful cloud-based servers.

This reliance on cloud computing poses significant security risks, particularly in areas like health care, where hospitals may be hesitant to use AI tools to analyze confidential patient data due to privacy concerns.

To tackle this pressing issue, MIT researchers have developed a security protocol that leverages the quantum properties of light to guarantee that data sent to and from a cloud server remain secure during deep-learning computations.

By encoding data into the laser light used in fiber optic communications systems, the protocol exploits the fundamental principles of quantum mechanics, making it impossible for attackers to copy or intercept the information without detection.

Moreover, the technique guarantees security without compromising the accuracy of the deep-learning models. In tests, the researcher demonstrated that their protocol could maintain 96 percent accuracy while ensuring robust security measures.

“Deep learning models like GPT-4 have unprecedented capabilities but require massive computational resources. Our protocol enables users to harness these powerful models without compromising the privacy of their data or the proprietary nature of the models themselves,” says Kfir Sulimany, an MIT postdoc in the Research Laboratory for Electronics (RLE) and lead author of a paper on this security protocol.

Sulimany is joined on the paper by Sri Krishna Vadlamani, an MIT postdoc; Ryan Hamerly, a former postdoc now at NTT Research, Inc.; Prahlad Iyengar, an electrical engineering and computer science (EECS) graduate student; and senior author Dirk Englund, a professor in EECS, principal investigator of the Quantum Photonics and Artificial Intelligence Group and of RLE. The research was recently presented at Annual Conference on Quantum Cryptography.

A two-way street for security in deep learning

The cloud-based computation scenario the researchers focused on involves two parties — a client that has confidential data, like medical images, and a central server that controls a deep learning model.

The client wants to use the deep-learning model to make a prediction, such as whether a patient has cancer based on medical images, without revealing information about the patient.

In this scenario, sensitive data must be sent to generate a prediction. However, during the process the patient data must remain secure.

Also, the server does not want to reveal any parts of the proprietary model that a company like OpenAI spent years and millions of dollars building.

“Both parties have something they want to hide,” adds Vadlamani.

In digital computation, a bad actor could easily copy the data sent from the server or the client.

Quantum information, on the other hand, cannot be perfectly copied. The researchers leverage this property, known as the no-cloning principle, in their security protocol.

For the researchers’ protocol, the server encodes the weights of a deep neural network into an optical field using laser light.

A neural network is a deep-learning model that consists of layers of interconnected nodes, or neurons, that perform computation on data. The weights are the components of the model that do the mathematical operations on each input, one layer at a time. The output of one layer is fed into the next layer until the final layer generates a prediction.

The server transmits the network’s weights to the client, which implements operations to get a result based on their private data. The data remain shielded from the server.

At the same time, the security protocol allows the client to measure only one result, and it prevents the client from copying the weights because of the quantum nature of light.

Once the client feeds the first result into the next layer, the protocol is designed to cancel out the first layer so the client can’t learn anything else about the model.

“Instead of measuring all the incoming light from the server, the client only measures the light that is necessary to run the deep neural network and feed the result into the next layer. Then the client sends the residual light back to the server for security checks,” Sulimany explains.

Due to the no-cloning theorem, the client unavoidably applies tiny errors to the model while measuring its result. When the server receives the residual light from the client, the server can measure these errors to determine if any information was leaked. Importantly, this residual light is proven to not reveal the client data.

A practical protocol

Modern telecommunications equipment typically relies on optical fibers to transfer information because of the need to support massive bandwidth over long distances. Because this equipment already incorporates optical lasers, the researchers can encode data into light for their security protocol without any special hardware.

When they tested their approach, the researchers found that it could guarantee security for server and client while enabling the deep neural network to achieve 96 percent accuracy.

The tiny bit of information about the model that leaks when the client performs operations amounts to less than 10 percent of what an adversary would need to recover any hidden information. Working in the other direction, a malicious server could only obtain about 1 percent of the information it would need to steal the client’s data.

“You can be guaranteed that it is secure in both ways — from the client to the server and from the server to the client,” Sulimany says.

“A few years ago, when we developed our demonstration of distributed machine learning inference between MIT’s main campus and MIT Lincoln Laboratory, it dawned on me that we could do something entirely new to provide physical-layer security, building on years of quantum cryptography work that had also been shown on that testbed,” says Englund. “However, there were many deep theoretical challenges that had to be overcome to see if this prospect of privacy-guaranteed distributed machine learning could be realized. This didn’t become possible until Kfir joined our team, as Kfir uniquely understood the experimental as well as theory components to develop the unified framework underpinning this work.”

In the future, the researchers want to study how this protocol could be applied to a technique called federated learning, where multiple parties use their data to train a central deep-learning model. It could also be used in quantum operations, rather than the classical operations they studied for this work, which could provide advantages in both accuracy and security.

“This work combines in a clever and intriguing way techniques drawing from fields that do not usually meet, in particular, deep learning and quantum key distribution. By using methods from the latter, it adds a security layer to the former, while also allowing for what appears to be a realistic implementation. This can be interesting for preserving privacy in distributed architectures. I am looking forward to seeing how the protocol behaves under experimental imperfections and its practical realization,” says Eleni Diamanti, a CNRS research director at Sorbonne University in Paris, who was not involved with this work.

This work was supported, in part, by the Israeli Council for Higher Education and the Zuckerman STEM Leadership Program.



de MIT News https://ift.tt/u8ehVZk

Mars’ missing atmosphere could be hiding in plain sight

Mars wasn’t always the cold desert we see today. There’s increasing evidence that water once flowed on the Red Planet’s surface, billions of years ago. And if there was water, there must also have been a thick atmosphere to keep that water from freezing. But sometime around 3.5 billion years ago, the water dried up, and the air, once heavy with carbon dioxide, dramatically thinned, leaving only the wisp of an atmosphere that clings to the planet today.

Where exactly did Mars’ atmosphere go? This question has been a central mystery of Mars’ 4.6-billion-year history.

For two MIT geologists, the answer may lie in the planet’s clay. In a paper appearing today in Science Advances, they propose that much of Mars’ missing atmosphere could be locked up in the planet’s clay-covered crust.

The team makes the case that, while water was present on Mars, the liquid could have trickled through certain rock types and set off a slow chain of reactions that progressively drew carbon dioxide out of the atmosphere and converted it into methane — a form of carbon that could be stored for eons in the planet’s clay surface.

Similar processes occur in some regions on Earth. The researchers used their knowledge of interactions between rocks and gases on Earth and applied that to how similar processes could play out on Mars. They found that, given how much clay is estimated to cover Mars’ surface, the planet’s clay could hold up to 1.7 bar of carbon dioxide, which would be equivalent to around 80 percent of the planet’s initial, early atmosphere.

It’s possible that this sequestered Martian carbon could one day be recovered and converted into propellant to fuel future missions between Mars and Earth, the researchers propose.

“Based on our findings on Earth, we show that similar processes likely operated on Mars, and that copious amounts of atmospheric CO2 could have transformed to methane and been sequestered in clays,” says study author Oliver Jagoutz, professor of geology in MIT’s Department of Earth, Atmospheric and Planetary Sciences (EAPS). “This methane could still be present and maybe even used as an energy source on Mars in the future.”

The study’s lead author is recent EAPS graduate Joshua Murray PhD ’24.

In the folds

Jagoutz’ group at MIT seeks to identify the geologic processes and interactions that drive the evolution of Earth’s lithosphere — the hard and brittle outer layer that includes the crust and upper mantle, where tectonic plates lie.

In 2023, he and Murray focused on a type of surface clay mineral called smectite, which is known to be a highly effective trap for carbon. Within a single grain of smectite are a multitude of folds, within which carbon can sit undisturbed for billions of years. They showed that smectite on Earth was likely a product of tectonic activity, and that, once exposed at the surface, the clay minerals acted to draw down and store enough carbon dioxide from the atmosphere to cool the planet over millions of years.

Soon after the team reported their results, Jagoutz happened to look at a map of the surface of Mars and realized that much of that planet’s surface was covered in the same smectite clays. Could the clays have had a similar carbon-trapping effect on Mars, and if so, how much carbon could the clays hold?

“We know this process happens, and it is well-documented on Earth. And these rocks and clays exist on Mars,” Jagoutz says. “So, we wanted to try and connect the dots.”

“Every nook and cranny”

Unlike on Earth, where smectite is a consequence of continental plates shifting and uplifting to bring rocks from the mantle to the surface, there is no such tectonic activity on Mars. The team looked for ways in which the clays could have formed on Mars, based on what scientists know of the planet’s history and composition.

For instance, some remote measurements of Mars’ surface suggest that at least part of the planet’s crust contains ultramafic igneous rocks, similar to those that produce smectites through weathering on Earth. Other observations reveal geologic patterns similar to terrestrial rivers and tributaries, where water could have flowed and reacted with the underlying rock.

Jagoutz and Murray wondered whether water could have reacted with Mars’ deep ultramafic rocks in a way that would produce the clays that cover the surface today. They developed a simple model of rock chemistry, based on what is known of how igneous rocks interact with their environment on Earth.

They applied this model to Mars, where scientists believe the crust is mostly made up of igneous rock that is rich in the mineral olivine. The team used the model to estimate the changes that olivine-rich rock might undergo, assuming that water existed on the surface for at least a billion years, and the atmosphere was thick with carbon dioxide.

“At this time in Mars’ history, we think CO2 is everywhere, in every nook and cranny, and water percolating through the rocks is full of CO2 too,” Murray says.

Over about a billion years, water trickling through the crust would have slowly reacted with olivine — a mineral that is rich in a reduced form of iron. Oxygen molecules in water would have bound to the iron, releasing hydrogen as a result and forming the red oxidized iron which gives the planet its iconic color. This free hydrogen would then have combined with carbon dioxide in the water, to form methane. As this reaction progressed over time, olivine would have slowly transformed into another type of iron-rich rock known as serpentine, which then continued to react with water to form smectite.

“These smectite clays have so much capacity to store carbon,” Murray says. “So then we used existing knowledge of how these minerals are stored in clays on Earth, and extrapolate to say, if the Martian surface has this much clay in it, how much methane can you store in those clays?”

He and Jagoutz found that if Mars is covered in a layer of smectite that is 1,100 meters deep, this amount of clay could store a huge amount of methane, equivalent to most of the carbon dioxide in the atmosphere that is thought to have disappeared since the planet dried up.

“We find that estimates of global clay volumes on Mars are consistent with a significant fraction of Mars’ initial CO2 being sequestered as organic compounds within the clay-rich crust,” Murray says. “In some ways, Mars’ missing atmosphere could be hiding in plain sight.”

“Where the CO2 went from an early, thicker atmosphere is a fundamental question in the history of the Mars atmosphere, its climate, and the habitability by microbes,” says Bruce Jakosky, professor emeritus of geology at the University of Colorado and principal investigator on the Mars Atmosphere and Volatile Evolution (MAVEN) mission, which has been orbiting and studying Mars’ upper atmosphere since 2014. Jakosky was not involved with the current study. “Murray and Jagoutz examine the chemical interaction of rocks with the atmosphere as a means of removing CO2. At the high end of our estimates of how much weathering has occurred, this could be a major process in removing CO2 from Mars’ early atmosphere.”

This work was supported, in part, by the National Science Foundation.



de MIT News https://ift.tt/y2mfvZC

martes, 24 de septiembre de 2024

Startup helps people fall asleep by aligning audio signals with brainwaves

Do you ever toss and turn in bed after a long day, wishing you could just program your brain to turn off and get some sleep?

That may sound like science fiction, but that’s the goal of the startup Elemind, which is using an electroencephalogram (EEG) headband that emits acoustic stimulation aligned with people’s brainwaves to move them into a sleep state more quickly.

In a small study of adults with sleep onset insomnia, 30 minutes of stimulation from the device decreased the time it took them to fall asleep by 10 to 15 minutes. This summer, Elemind began shipping its product to a small group of users as part of an early pilot program.

The company, which was founded by MIT Professor Ed Boyden ’99, MNG ’99; David Wang ’05, SM ’10, PhD ’15; former postdoc Nir Grossman; former Media Lab research affiliate Heather Read; and Meredith Perry, plans to collect feedback from early users before making the device more widely available.

Elemind’s team believes their device offers several advantages over sleeping pills that can cause side effects and addiction.

“We wanted to create a nonchemical option for people who wanted to get great sleep without side effects, so you could get all the benefits of natural sleep without the risks,” says Perry, Elemind’s CEO. “There’s a number of people that we think would benefit from this device, whether you’re a breastfeeding mom that might not want to take a sleep drug, somebody traveling across time zones that wants to fight jet lag, or someone that simply wants to improve your next-day performance and feel like you have more control over your sleep.”

From research to product

Wang’s academic journey at MIT spanned nearly 15 years, during which he earned four degrees, culminating in a PhD in artificial intelligence in 2015. In 2014, Wang was co-teaching a class with Grossman when they began working together to noninvasively measure real-time biological oscillations in the brain and body. Through that work, they became fascinated with a technique for modulating the brain known as phase-locked stimulation, which uses precisely timed visual, physical, or auditory stimulation that lines up with brain activity.

“You’re measuring some kind of changing variable, and then you want to change your stimulus in real time in response to that variable,” explains Boyden, who pointed Wang and Grossman to a set of mathematical techniques that became some of the core intellectual property of Elemind.

Phase-locked stimulation has been used in conjunction with electrodes implanted in the brain to disrupt seizures and tremors for years. But in 2021, Wang, Grossman, Boyden, and their collaborators published a paper showing they could use electrical stimulation from outside the skull to suppress essential tremor syndrome, the most common adult movement disorder.

The results were promising, but the founders decided to start by proving their approach worked in a less regulated space: sleep. They developed a system to deliver auditory pulses timed to promote or suppress alpha oscillations in the brain, which are elevated in insomnia.

That kicked off a years-long product development process that led to the headband device Elemind uses today. The headband measures brainwaves through EEG and feeds the results into Elemind's proprietary algorithms, which are used to dynamically generate audio through a bone conduction driver. The moment the device detects that someone is asleep, the audio is slowly tapered out.

“We have a theory that the sound that we play triggers an auditory-evoked response in the brain,” Wang says. “That means we get your auditory cortex to basically release this voltage burst that sweeps across your brain and interferes with other regions. Some people who have worn Elemind call it a brain jammer. For folks that ruminate a lot before they go to sleep, their brains are actively running. This encourages their brain to quiet down.”

Beyond sleep

Elemind has established a collaboration with eight universities that allows researchers to explore the effectiveness of the company’s approach in a range of use cases, from tremors to memory formation, Alzheimer’s progression, and more.

“We’re not only developing this product, but also advancing the field of neuroscience by collecting high-resolution data to hopefully also help others conduct new research,” Wang says.

The collaborations have led to some exciting results. Researchers at McGill University found that using Elemind’s acoustic stimulation during sleep increased activity in areas of the cortex related to motor function and improved healthy adults’ performance in memory tasks. Other studies have shown the approach can be used to reduce essential tremors in patients and enhance sedation recovery.

Elemind is focused on its sleep application for now, but the company plans to develop other solutions, from medical interventions to memory and focus augmentation, as the science evolves.

“The vision is how do we move beyond sleep into what could ultimately become like an app store for the brain, where you can download a brain state like you download an app?” Perry says. “How can we make this a tool that can be applied to a bunch of different applications with a single piece of hardware that has a lot of different stimulation protocols?”



de MIT News https://ift.tt/yG2icQ4

Research quantifying “nociception” could help improve management of surgical pain

The degree to which a surgical patient’s subconscious processing of pain, or “nociception,” is properly managed by their anesthesiologist will directly affect the degree of post-operative drug side effects they’ll experience and the need for further pain management they’ll require. But pain is a subjective feeling to measure, even when patients are awake, much less when they are unconscious. 

In a new study appearing in the Proceedings of the National Academy of Sciences, MIT and Massachusetts General Hospital (MGH) researchers describe a set of statistical models that objectively quantified nociception during surgery. Ultimately, they hope to help anesthesiologists optimize drug dose and minimize post-operative pain and side effects.

The new models integrate data meticulously logged over 18,582 minutes of 101 abdominal surgeries in men and women at MGH. Led by Sandya Subramanian PhD ’21, an assistant professor at the University of California at Berkeley and the University of California at San Francisco, the researchers collected and analyzed data from five physiological sensors as patients experienced a total of 49,878 distinct “nociceptive stimuli” (such as incisions or cautery). Moreover, the team recorded what drugs were administered, and how much and when, to factor in their effects on nociception or cardiovascular measures. They then used all the data to develop a set of statistical models that performed well in retrospectively indicating the body’s response to nociceptive stimuli.

The team’s goal is to furnish such accurate, objective, and physiologically principled information in real time to anesthesiologists who currently have to rely heavily on intuition and past experience in deciding how to administer pain-control drugs during surgery. If anesthesiologists give too much, patients can experience side effects ranging from nausea to delirium. If they give too little, patients may feel excessive pain after they awaken.

“Sandya’s work has helped us establish a principled way to understand and measure nociception (unconscious pain) during general anesthesia,” says study senior author Emery N. Brown, the Edward Hood Taplin Professor of Medical Engineering and Computational Neuroscience in The Picower Institute for Learning and Memory, the Institute for Medical Engineering and Science, and the Department of Brain and Cognitive Sciences at MIT. Brown is also an anesthesiologist at MGH and a professor at Harvard Medical School. “Our next objective is to make the insights that we have gained from Sandya’s studies reliable and practical for anesthesiologists to use during surgery.”

Surgery and statistics

The research began as Subramanian’s doctoral thesis project in Brown’s lab in 2017. The best prior attempts to objectively model nociception have either relied solely on the electrocardiogram (ECG, an indirect indicator of heart-rate variability) or other systems that may incorporate more than one measurement, but were either based on lab experiments using pain stimuli that do not compare in intensity to surgical pain or were validated by statistically aggregating just a few time points across multiple patients’ surgeries, Subramanian says.

“There’s no other place to study surgical pain except for the operating room,” Subramanian says. “We wanted to not only develop the algorithms using data from surgery, but also actually validate it in the context in which we want someone to use it. If we are asking them to track moment-to-moment nociception during an individual surgery, we need to validate it in that same way.”

So she and Brown worked to advance the state of the art by collecting multi-sensor data during the whole course of actual surgeries and by accounting for the confounding effects of the drugs administered. In that way, they hoped to develop a model that could make accurate predictions that remained valid for the same patient all the way through their operation.

Part of the improvements the team achieved arose from tracking patterns of heart rate and also skin conductance. Changes in both of these physiological factors can be indications of the body’s primal “fight or flight” response to nociception or pain, but some drugs used during surgery directly affect cardiovascular state, while skin conductance (or “EDA,” electrodermal activity) remains unaffected. The study measures not only ECG but also backs it up with PPG, an optical measure of heart rate (like the oxygen sensor on a smartwatch), because ECG signals can sometimes be made noisy by all the electrical equipment buzzing away in the operating room. Similarly, Subramanian backstopped EDA measures with measures of skin temperature to ensure that changes in skin conductance from sweat were because of nociception and not simply the patient being too warm. The study also tracked respiration.

Then the authors performed statistical analyses to develop physiologically relevant indices from each of the cardiovascular and skin conductance signals. And once each index was established, further statistical analysis enabled tracking the indices together to produce models that could make accurate, principled predictions of when nociception was occurring and the body’s response.

Nailing nociception

In four versions of the model, Subramanian “supervised” them by feeding them information on when actual nociceptive stimuli occurred so that they could then learn the association between the physiological measurements and the incidence of pain-inducing events. In some of these trained versions she left out drug information and in some versions she used different statistical approaches (either “linear regression” or “random forest”). In a fifth version of the model, based on a “state space” approach, she left it unsupervised, meaning it had to learn to infer moments of nociception purely from the physiological indices. She compared all five versions of her model to one of the current industry standards, an ECG-tracking model called ANI.

Each model’s output can be visualized as a graph plotting the predicted degree of nociception over time. ANI performs just above chance but is implemented in real-time. The unsupervised model performed better than ANI, though not quite as well as the supervised models. The best performing of those was one that incorporated drug information and used a “random forest” approach. Still, the authors note, the fact that the unsupervised model performed significantly better than chance suggests that there is indeed an objectively detectable signature of the body’s nociceptive state even when looking across different patients.

“A state space framework using multisensory physiological observations is effective in uncovering this implicit nociceptive state with a consistent definition across multiple subjects,” wrote Subramanian, Brown, and their co-authors. “This is an important step toward defining a metric to track nociception without including nociceptive ‘ground truth’ information, most practical for scalability and implementation in clinical settings.”

Indeed, the next steps for the research are to increase the data sampling and to further refine the models so that they can eventually be put into practice in the operating room. That will require enabling them to predict nociception in real time, rather than in post-hoc analysis. When that advance is made, that will enable anesthesiologists or intensivists to inform their pain drug dosing judgements. Further into the future, the model could inform closed-loop systems that automatically dose drugs under the anesthesiologist’s supervision.

“Our study is an important first step toward developing objective markers to track surgical nociception,” the authors concluded. “These markers will enable objective assessment of nociception in other complex clinical settings, such as the ICU [intensive care unit], as well as catalyze future development of closed-loop control systems for nociception.”

In addition to Subramanian and Brown, the paper’s other authors are Bryan Tseng, Marcela del Carmen, Annekathryn Goodman, Douglas Dahl, and Riccardo Barbieri.

Funding from The JPB Foundation; The Picower Institute; George J. Elbaum ’59, SM ’63, PhD ’67; Mimi Jensen; Diane B. Greene SM ’78; Mendel Rosenblum; Bill Swanson; Cathy and Lou Paglia; annual donors to the Anesthesia Initiative Fund; the National Science Foundation; and an MIT Office of Graduate Education Collabmore-Rogers Fellowship supported the research.



de MIT News https://ift.tt/rgkjlPD

3 Questions: Should we label AI systems like we do prescription drugs?

AI systems are increasingly being deployed in safety-critical health care situations. Yet these models sometimes hallucinate incorrect information, make biased predictions, or fail for unexpected reasons, which could have serious consequences for patients and clinicians.

In a commentary article published today in Nature Computational Science, MIT Associate Professor Marzyeh Ghassemi and Boston University Associate Professor Elaine Nsoesie argue that, to mitigate these potential harms, AI systems should be accompanied by responsible-use labels, similar to U.S. Food and Drug Administration-mandated labels placed on prescription medications.

MIT News spoke with Ghassemi about the need for such labels, the information they should convey, and how labeling procedures could be implemented.

Q: Why do we need responsible use labels for AI systems in health care settings?

A: In a health setting, we have an interesting situation where doctors often rely on technology or treatments  that are not fully understood. Sometimes this lack of understanding is fundamental — the mechanism behind acetaminophen for instance — but other times this is just a limit of specialization. We don’t expect clinicians to know how to service an MRI machine, for instance. Instead, we have certification systems through the FDA or other federal agencies, that certify the use of a medical device or drug in a specific setting.

Importantly, medical devices also have service contracts — a technician from the manufacturer will fix your MRI machine if it is miscalibrated. For approved drugs, there are postmarket surveillance and reporting systems so that adverse effects or events can be addressed, for instance if a lot of people taking a drug seem to be developing a condition or allergy.

Models and algorithms, whether they incorporate AI or not, skirt a lot of these approval and long-term monitoring processes, and that is something we need to be wary of. Many prior studies have shown that predictive models need more careful evaluation and monitoring. With more recent generative AI specifically, we cite work that has demonstrated generation is not guaranteed to be appropriate, robust, or unbiased. Because we don’t have the same level of surveillance on model predictions or generation, it would be even more difficult to catch a model’s problematic responses. The generative models being used by hospitals right now could be biased. Having use labels is one way of ensuring that models don’t automate biases that are learned from human practitioners or miscalibrated clinical decision support scores of the past.      

Q: Your article describes several components of a responsible use label for AI, following the FDA approach for creating prescription labels, including approved usage, ingredients, potential side effects, etc. What core information should these labels convey?

A: The things a label should make obvious are time, place, and manner of a model’s intended use. For instance, the user should know that models were trained at a specific time with data from a specific time point. For instance, does it include data that did or did not include the Covid-19 pandemic? There were very different health practices during Covid that could impact the data. This is why we advocate for the model “ingredients” and “completed studies” to be disclosed.

For place, we know from prior research that models trained in one location tend to have worse performance when moved to another location. Knowing where the data were from and how a model was optimized within that population can help to ensure that users are aware of “potential side effects,” any “warnings and precautions,” and “adverse reactions.”

With a model trained to predict one outcome, knowing the time and place of training could help you make intelligent judgements about deployment. But many generative models are incredibly flexible and can be used for many tasks. Here, time and place may not be as informative, and more explicit direction about “conditions of labeling” and “approved usage” versus “unapproved usage” come into play. If a developer has evaluated a generative model for reading a patient’s clinical notes and generating prospective billing codes, they can disclose that it has bias toward overbilling for specific conditions or underrecognizing others. A user wouldn’t want to use this same generative model to decide who gets a referral to a specialist, even though they could. This flexibility is why we advocate for additional details on the manner in which models should be used.

In general, we advocate that you should train the best model you can, using the tools available to you. But even then, there should be a lot of disclosure. No model is going to be perfect. As a society, we now understand that no pill is perfect — there is always some risk. We should have the same understanding of AI models. Any model — with or without AI — is limited. It may be giving you realistic, well-trained, forecasts of potential futures, but take that with whatever grain of salt is appropriate.

Q: If AI labels were to be implemented, who would do the labeling and how would labels be regulated and enforced?

A: If you don’t intend for your model to be used in practice, then the disclosures you would make for a high-quality research publication are sufficient. But once you intend your model to be deployed in a human-facing setting, developers and deployers should do an initial labeling, based on some of the established frameworks. There should be a validation of these claims prior to deployment; in a safety-critical setting like health care, many agencies of the Department of Health and Human Services could be involved.

For model developers, I think that knowing you will need to label the limitations of a system induces more careful consideration of the process itself. If I know that at some point I am going to have to disclose the population upon which a model was trained, I would not want to disclose that it was trained only on dialogue from male chatbot users, for instance.

Thinking about things like who the data are collected on, over what time period, what the sample size was, and how you decided what data to include or exclude, can open your mind up to potential problems at deployment. 



de MIT News https://ift.tt/9as8zwn

lunes, 23 de septiembre de 2024

MIT named No. 2 university by U.S. News for 2024-25

MIT has placed second in U.S. News and World Report’s annual rankings of the nation’s best colleges and universities, announced today. 

As in past years, MIT’s engineering program continues to lead the list of undergraduate engineering programs at a doctoral institution. The Institute also placed first in six out of nine engineering disciplines.

U.S. News placed MIT second in its evaluation of undergraduate computer science programs, along with Carnegie Mellon University and the University of California at Berkeley. The Institute placed first in four out of 10 computer science disciplines.

MIT remains the No. 2 undergraduate business program, a ranking it shares with UC Berkeley. Among business subfields, MIT is ranked first in three out of 10 specialties.

Within the magazine’s rankings of “academic programs to look for,” MIT topped the list in the category of undergraduate research and creative projects. The Institute also ranks as the third most innovative national university and the third best value, according to the U.S. News peer assessment survey of top academics.

MIT placed first in six engineering specialties: aerospace/aeronautical/astronautical engineering; chemical engineering; computer engineering; electrical/electronic/communication engineering; materials engineering; and mechanical engineering. It placed within the top five in two other engineering areas: biomedical engineering and civil engineering.

Other schools in the top five overall for undergraduate engineering programs are Stanford University, UC Berkeley, Georgia Tech, Caltech, the University of Illinois at Urbana-Champaign, and the University of Michigan at Ann Arbor.

In computer science, MIT placed first in four specialties: biocomputing/bioinformatics/biotechnology; computer systems; programming languages; and theory. It placed in the top five of five other disciplines: artificial intelligence; cybersecurity; data analytics/science; mobile/web applications; and software engineering.

The No. 1-ranked undergraduate computer science program overall is at Stanford. Other schools in the top five overall for undergraduate computer science programs are Carnegie Mellon, Stanford, UC Berkeley, Princeton University, and the University of Illinois at Urbana-Champaign.

Among undergraduate business specialties, the MIT Sloan School of Management leads in analytics; production/operations management; and quantitative analysis. It also placed within the top five in three other categories: entrepreneurship; management information systems; and supply chain management/logistics.

The No. 1-ranked undergraduate business program overall is at the University of Pennsylvania; other schools ranking in the top five include UC Berkeley, the University of Michigan at Ann Arbor, and New York University.



de MIT News https://ift.tt/EzW6bOK

Playing a new tune

For generations, Andrew Sutherland’s family had the same calling: bagpipes. Growing up in Halifax, Nova Scotia, in a family with Scottish roots, Sutherland’s father, grandfather, and great-grandfather all played the bagpipes competitively, criss-crossing North America. Sutherland’s aunts and uncles were pipers too.

But Sutherland did not take to the instrument. He liked math, went to college, entered a PhD program, and emerged as a professor at the MIT Sloan School of Management. Sutherland is an enterprising scholar whose work delves into issues around the financing and auditing of private firms, the effects of financial technology, and even detecting business fraud.

“I was actually the first male in my family to not play the bagpipes, and the first to go to university,” Sutherland explains. “The joke is that I’m the shame of the family, since I never picked up the pipes and continued the tradition.”

The family bagpiping loss is MIT’s gain. While Sutherland’s area of specialty is nominally accounting, his work has illuminated business practices more broadly.

“A lot of what we know about the financial system and how companies perform, and about financial statements, comes from big public companies,” Sutherland says. “But we have a lot of entrepreneurs come through Sloan looking to found startups, and in the U.S., private firms generate more than half of employment and investment. Until recently, we haven’t known a lot about how they get capital, how they make decisions.”

For his research and teaching, Sutherland was awarded tenure at MIT last year.

Piper at the gates of college

Sutherland is proud of his family history; his grandfather and great-grandfather have taught generations of bagpipe players in Nova Scotia, with many of their students becoming successful pipers around the world. But Sutherland took to math and business studies, receiving his undergraduate degree in commerce, with honors in accounting, from York University in Toronto. Then he received an MBA from Carnegie Mellon University, with concentrations in finance and quantitative analysis.

Sutherland still wanted to research financial markets, though. How did banks evaluate the private businesses they were lending to? How much were those firms disclosing to investors? How much just comes down to trust? He entered the PhD program at the University of Chicago’s Booth School of Business and found scholars encouraging him to pursue those questions.

That included Sutherland’s advisor, Christian Leuz; the long-time Chicago professor Douglas Diamond, now a Nobel Prize winner, whom Sutherland calls “one of the most generous researchers I’ve met” in academia; and a then-assistant professor, Michael Minnis, who shared Sutherland’s interest in studying private firms and entrepreneurs.

Sutherland earned his PhD from Chicago in 2015, with a dissertation about the changing nature of banker-to-business relationships, published in 2018. That research studied the effects of transparency-improving technologies on how small businesses obtained credit.

“Twenty years ago, banking was very relationship-based,” Sutherland says. “You might play golf with your loan officer once a year and they knew your business and maybe your employees, and they would sponsor the local softball team. Whereas now banking has been really influenced by technology. A lot of companies provide credit through online applications, and the days where you had to supply audited financial statements has gone away.” As a result of the expansion in technology-based lending, credit markets have shifted from a relationship basis to a transactional focus.

Sutherland, who is currently an associate professor at MIT, joined the faculty in 2015 and has remained at the Institute ever since. A fan of modern art, his office at MIT Sloan includes an Andy Warhol print, which is part of MIT’s art-lending program, as well as reproductions of some of Harold “Doc” Edgerton’s famous high-speed photographs.

Sutherland has since written five papers with Minnis (now a deputy dean at Chicago Booth), and other co-authors. Many of their findings highlight the variation in lending and contracting practices in the small business sector. In a 2017 study, they found that banks collected fewer verified financial statements from construction companies during the pre-2008 housing bubble than afterward; before 2008, lending had become lax, similar to what happened in the mortgage markets, and this contributed to the crisis. In another study from that year, they showed how banks with extensive industry and geographic expertise rely more on soft than hard information in lending.

“We’re trying to understand the ‘Wild West’ in accounting and finance more broadly,” Sutherland says. “For firms like entrepreneurs and privately held companies, largely unfettered by regulation, what choices do they make, and why? And how can we use economic theory to understand these choices?”

Business, trust, and fraud

Indeed, Sutherland has often homed in on issues around trust, rules, and financial misconduct, something students care about greatly.

“Students are always interested in talking about fraud,” Sutherland says. “Our financial system is based on trust. So many of us invest on an entirely anonymous basis — we don’t personally know our fund manager or closely watch what they do with our money.” And while regulations and a functioning justice system protect against problems, Sutherland notes, finance works partly because “people have some trust in the financial system. But that’s a fragile thing. Once people are swindled, they just keep their money in the bank or under the mattress. Often we’ll have students from countries with weak institutions or corruption, and they’ll say, ‘You would never do the things you can do in the U.S., in terms of investing your money.’ Without trust, it becomes harder for entrepreneurs to raise capital and undermines the whole vibrant economic system we have.”

Some measures can make a big difference. In a 2020 paper published in the Journal of Financial Economics, Sutherland and two co-authors found that a 2010 change to the investment adviser qualification exam, which reduced its focus on ethics, had significant effects: People who passed the exam when it featured more rules and ethics material are one-fourth less likely to commit misconduct. They are also more likely to depart employers during or even before scandals.

“It does seem to matter,” Sutherland says. “The person who has had less ethics training is more likely to get in trouble with the industry. You can predict future fraud in a firm by who is quitting. Those with more ethics training are more likely to leave before a scandal breaks.”

In the classroom

Sutherland also believes his interests are well-suited to the MIT Sloan School of Management, since many students are looking to found startups.

“One thing that really stands out about Sloan is that we attract a lot of entrepreneurs,” Sutherland says. “They’re curious about all this stuff: How do I get financing? Should I go to a bank? Should I raise equity? How do I compare myself to competitors? It’s striking to me that if that person wanted to work for a big public firm, I could hand them a textbook that answers many of these questions. But when it comes to private firms, a lot of that is unknown. And it motivates me to find answers.”

And while Sutherland is a prolific researcher, he views classroom time as being just as important. 

“What I hope with every project I work on is that I could take the findings to the classroom, and the students would find it relevant and interesting,” Sutherland says.

As much as Sutherland made a big departure from the family business, he still gets to teach, and in a sense perform for an audience. Ask Sutherland about his students, and he sounds an emphatically upbeat note.

“One of the best things about teaching at MIT,” Sutherland says, “is that the students are smart enough that you can explain how you did the study, and someone will put up a hand and say: ‘What about this, or that?’ You can bring research findings to the classroom and they absorb them and challenge you on them. It’s the best place in the world to teach, because the students are just so curious and so smart.”



de MIT News https://ift.tt/Jp0mA7Q

Accelerating particle size distribution estimation

The pharmaceutical manufacturing industry has long struggled with the issue of monitoring the characteristics of a drying mixture, a critical step in producing medication and chemical compounds. At present, there are two noninvasive characterization approaches that are typically used: A sample is either imaged and individual particles are counted, or researchers use a scattered light to estimate the particle size distribution (PSD). The former is time-intensive and leads to increased waste, making the latter a more attractive option.

In recent years, MIT engineers and researchers developed a physics and machine learning-based scattered light approach that has been shown to improve manufacturing processes for pharmaceutical pills and powders, increasing efficiency and accuracy and resulting in fewer failed batches of products. A new open-access paper, “Non-invasive estimation of the powder size distribution from a single speckle image,” available in the journal Light: Science & Application, expands on this work, introducing an even faster approach. 

“Understanding the behavior of scattered light is one of the most important topics in optics,” says Qihang Zhang PhD ’23, an associate researcher at Tsinghua University. “By making progress in analyzing scattered light, we also invented a useful tool for the pharmaceutical industry. Locating the pain point and solving it by investigating the fundamental rule is the most exciting thing to the research team.”

The paper proposes a new PSD estimation method, based on pupil engineering, that reduces the number of frames needed for analysis. “Our learning-based model can estimate the powder size distribution from a single snapshot speckle image, consequently reducing the reconstruction time from 15 seconds to a mere 0.25 seconds,” the researchers explain.

“Our main contribution in this work is accelerating a particle size detection method by 60 times, with a collective optimization of both algorithm and hardware,” says Zhang. “This high-speed probe is capable to detect the size evolution in fast dynamical systems, providing a platform to study models of processes in pharmaceutical industry including drying, mixing and blending.”

The technique offers a low-cost, noninvasive particle size probe by collecting back-scattered light from powder surfaces. The compact and portable prototype is compatible with most of drying systems in the market, as long as there is an observation window. This online measurement approach may help control manufacturing processes, improving efficiency and product quality. Further, the previous lack of online monitoring prevented systematical study of dynamical models in manufacturing processes. This probe could bring a new platform to carry out series research and modeling for the particle size evolution.

This work, a successful collaboration between physicists and engineers, is generated from the MIT-Takeda program. Collaborators are affiliated with three MIT departments: Mechanical Engineering, Chemical Engineering, and Electrical Engineering and Computer Science. George Barbastathis, professor of mechanical engineering at MIT, is the article’s senior author.



de MIT News https://ift.tt/OAbNecs

viernes, 20 de septiembre de 2024

A two-dose schedule could make HIV vaccines more effective

One major reason why it has been difficult to develop an effective HIV vaccine is that the virus mutates very rapidly, allowing it to evade the antibody response generated by vaccines.

Several years ago, MIT researchers showed that administering a series of escalating doses of an HIV vaccine over a two-week period could help overcome a part of that challenge by generating larger quantities of neutralizing antibodies. However, a multidose vaccine regimen administered over a short time is not practical for mass vaccination campaigns.

In a new study, the researchers have now found that they can achieve a similar immune response with just two doses, given one week apart. The first dose, which is much smaller, prepares the immune system to respond more powerfully to the second, larger dose.

This study, which was performed by bringing together computational modeling and experiments in mice, used an HIV envelope protein as the vaccine. A single-dose version of this vaccine is now in clinical trials, and the researchers hope to establish another study group that will receive the vaccine on a two-dose schedule.

“By bringing together the physical and life sciences, we shed light on some basic immunological questions that helped develop this two-dose schedule to mimic the multiple-dose regimen,” says Arup Chakraborty, the John M. Deutch Institute Professor at MIT and a member of MIT’s Institute for Medical Engineering and Science and the Ragon Institute of MIT, MGH and Harvard University.

This approach may also generalize to vaccines for other diseases, Chakraborty notes.

Chakraborty and Darrell Irvine, a former MIT professor of biological engineering and materials science and engineering and member of the Koch Institute for Integrative Cancer Research, who is now a professor of immunology and microbiology at the Scripps Research Institute, are the senior authors of the study, which appears today in Science Immunology. The lead authors of the paper are Sachin Bhagchandani PhD ’23 and Leerang Yang PhD ’24.

Neutralizing antibodies

Each year, HIV infects more than 1 million people around the world, and some of those people do not have access to antiviral drugs. An effective vaccine could prevent many of those infections. One promising vaccine now in clinical trials consists of an HIV protein called an envelope trimer, along with a nanoparticle called SMNP. The nanoparticle, developed by Irvine’s lab, acts as an adjuvant that helps recruit a stronger B cell response to the vaccine.

In clinical trials, this vaccine and other experimental vaccines have been given as just one dose. However, there is growing evidence that a series of doses is more effective at generating broadly neutralizing antibodies. The seven-dose regimen, the researchers believe, works well because it mimics what happens when the body is exposed to a virus: The immune system builds up a strong response as more viral proteins, or antigens, accumulate in the body.

In the new study, the MIT team investigated how this response develops and explored whether they could achieve the same effect using a smaller number of vaccine doses.

“Giving seven doses just isn’t feasible for mass vaccination,” Bhagchandani says. “We wanted to identify some of the critical elements necessary for the success of this escalating dose, and to explore whether that knowledge could allow us to reduce the number of doses.”

The researchers began by comparing the effects of one, two, three, four, five, six, or seven doses, all given over a 12-day period. They initially found that while three or more doses generated strong antibody responses, two doses did not. However, by tweaking the dose intervals and ratios, the researchers discovered that giving 20 percent of the vaccine in the first dose and 80 percent in a second dose, seven days later, achieved just as good a response as the seven-dose schedule.

“It was clear that understanding the mechanisms behind this phenomenon would be crucial for future clinical translation,” Yang says. “Even if the ideal dosing ratio and timing may differ for humans, the underlying mechanistic principles will likely remain the same.”

Using a computational model, the researchers explored what was happening in each of these dosing scenarios. This work showed that when all of the vaccine is given as one dose, most of the antigen gets chopped into fragments before it reaches the lymph nodes. Lymph nodes are where B cells become activated to target a particular antigen, within structures known as germinal centers.

When only a tiny amount of the intact antigen reaches these germinal centers, B cells can’t come up with a strong response against that antigen.

However, a very small number of B cells do arise that produce antibodies targeting the intact antigen. So, giving a small amount in the first dose does not “waste” much antigen but allows some B cells and antibodies to develop. If a second, larger dose is given a week later, those antibodies bind to the antigen before it can be broken down and escort it into the lymph node. This allows more B cells to be exposed to that antigen and eventually leads to a large population of B cells that can target it.

“The early doses generate some small amounts of antibody, and that’s enough to then bind to the vaccine of the later doses, protect it, and target it to the lymph node. That's how we realized that we don't need to give seven doses,” Bhagchandani says. “A small initial dose will generate this antibody and then when you give the larger dose, it can again be protected because that antibody will bind to it and traffic it to the lymph node.”

T-cell boost

Those antigens may stay in the germinal centers for weeks or even longer, allowing more B cells to come in and be exposed to them, making it more likely that diverse types of antibodies will develop.

The researchers also found that the two-dose schedule induces a stronger T-cell response. The first dose activates dendritic cells, which promote inflammation and T-cell activation. Then, when the second dose arrives, even more dendritic cells are stimulated, further boosting the T-cell response.

Overall, the two-dose regimen resulted in a fivefold improvement in the T-cell response and a 60-fold improvement in the antibody response, compared to a single vaccine dose.

“Reducing the ‘escalating dose’ strategy down to two shots makes it much more practical for clinical implementation. Further, a number of technologies are in development that could mimic the two-dose exposure in a single shot, which could become ideal for mass vaccination campaigns,” Irvine says.

The researchers are now studying this vaccine strategy in a nonhuman primate model. They are also working on specialized materials that can deliver the second dose over an extended period of time, which could further enhance the immune response.

The research was funded by the Koch Institute Support (core) Grant from the National Cancer Institute, the National Institutes of Health, and the Ragon Institute of MIT, MGH, and Harvard.



de MIT News https://ift.tt/mzOdIU3