Computer Science and Artificial Intelligence Laboratory (CSAIL)

A review led Prof. Marzyeh Ghassemi has found that a major issue in health-related machine learning models “is the relative scarcity of publicly available data sets in medicine,” reports Emily Sohn for Nature.

Research affiliate Ramin Hasani speaks with Kimberly Adams of Marketplace about how he and his CSAIL colleagues solved a differential equation dating back to the early 1900s, enabling researchers to create an AI algorithm that can learn on the spot and adapt to evolving patterns. The new algorithm “will enable larger-scale brain simulations,” Hasani explains.

Nature reporter Elie Dolgin writes that a new study by MIT researchers explores the role of the gene variant APOE4 in Alzheimer’s, and finds that the gene is linked with faulty cholesterol processing in the brain, impacting the insulation around nerve cells and potentially causing memory and learning deficits. “The work suggests that drugs that restore the brain’s cholesterol processing could treat the disease,” writes Dolgin. 

Popular Science reporter Charlotte Hu writes that MIT researchers have developed a new machine learning model that can depict how the sound around a listener changes as they move through a certain space. “We’re mostly modeling the spatial acoustics, so the [focus is on] reverberations,” explains graduate student Yilun Du. “Maybe if you’re in a concert hall, there are a lot of reverberations, maybe if you’re in a cathedral, there are many echoes versus if you’re in a small room, there isn’t really any echo.”

MIT researchers have developed a new technique aimed at protecting images from AI generators, reports Kyle Barr for Gizmodo. The program uses "data poisoning techniques to essentially disturb pixels within an image to create invisible noise, effectively making AI art generators incapable of generating realistic deepfakes based on the photos they’re fed,” reports Kyle Barr for Gizmodo." 

Prof. Emeritus Tim Berners-Lee spoke at Lisbon’s Web Summit conference about Solid, an “open-sourced gambit to reinvent the web through new decentralized privacy-minded tools for wrangling data,” reports Harry McCracken for Fast Company. Solid was originally started as an MIT research project.

Scientists at MIT have developed “a machine learning model that can capture how sounds in a room will propagate through space,” report Kyle Wiggers and Devin Coldewey for TechCrunch. “By modeling the acoustics, the system can learn a room’s geometry from sound recordings, which can then be used to build a visual rendering of a room,” write Wiggers and Coldewey.

MIT researchers have developed a new machine learning model that can identify and track blobs of plasma created in controlled nuclear-fusion research, reports Ed Browne for Newsweek. “Fusion research is a complex, multidisciplinary project that requires technologies from many fields,” explains graduate student Woonghee “Harry” Han.

Prof. Peter Shor has been named one of the winners of the 2023 Breakthrough Prize in Fundamental Physics, reports Nature. “Shor’s most renowned contribution is the development of quantum algorithms for prime number factorization,” writes Nature.

Prof. Daniela Rus, director of CSAIL, speaks with Forbes reporter John Koetsier about the future of robotics. “I have been on a quest to have universal machines,” says Rus. “My idea is to create universal robot cells that could combine to form different types of machines, each with the same capability.”

Researchers at MIT are working on a system that can track the development of Parkinson’s disease by monitoring a person’s gait speed, reports Kyle Wiggers and Devin Coldewey for TechCrunch. “The MIT Parkinson’s-tracking effort aims to help clinicians overcome challenges in treating the estimated 10 million people afflicted by the disease globally,” writes Wiggers and Coldewey.

Writing for The Hill, Prof. Daniela Rus, director of CSAIL, explores how automation could ease the supply chain crisis. “Automation in these settings doesn’t mean replacing employees, but developing more robust inventory management software and using systems like scanners and conveyors that make our jobs easier,” writes Rus. “This would enable warehouse workers to focus on other more detail-oriented roles, from overseeing the operation of forklifts to improving the efficiencies of distribution centers.”

MIT’s mini cheetah robot was taught how to goal keep using simulation, reports Emmett Smith for Mashable. “The robot was able to block 87.5 percent of the shots taken, which is just slightly above the best professional goalies in the English Premiere League,” writes Smith.

In a new paper, MIT researchers detail the use of reinforcement learning to teach MIT’s mini cheetah robot to play goalie in a soccer match, reports Brian Heater for TechCrunch. “In this work, we focused solely on the goalkeeping task, but the proposed framework can be extended to other scenarios, such as multi-skill soccer ball kicking,” the researchers explain.

Researchers from MIT and the Amsterdam Institute for Advanced Metropolitan Solutions have been developing an electric autonomous trash boat, reports Sarah Holder for Bloomberg. The boats “could reduce noise, pollution, and congestion, thus improving the quality of Amsterdam’s historic cityscape.”