STAT reporter Katie Palmer writes that MIT researchers have developed a new machine learning model that can "flag treatments for sepsis patients that are likely to lead to a ‘medical dead-end,/ the point after which a patient will die no matter what care is provided.”
Researchers from MIT and other institutions have successfully uncovered the letterlocking technique that Mary, Queen of Scots, used to seal her final letter, reports NPR’s Tien Le. “The spiral lock requires more than 30 steps and involves cutting out a ‘lock,’ often resembling a dagger or sword, out of the blank margin of the letter,” writes Le. “The lock acts as a needle and is sewn through the letter after folding it.”
MIT researchers have created a virtual environment for optimizing the design and control of soft robots, reports Prachi Patel for Scientific American. “The future goal is to take any task and say, ‘Design me an optimal robot to complete this task,’” says undergraduate Jagdeep Bhatia.
An international team of researchers has found that Mary, Queen of Scots, used a complicated paper-folding technique called letterlocking to conceal the contents of her final letter, reports Alison Flood for The Guardian. MIT Libraries Conservator Jana Dambrogio explains that working on Mary's last letter “and figuring out its unique spiral lock was thrilling as a researcher – and a real a-ha! moment in the study of letterlocking.”
Tech Crunch reporter Brian Heater spotlights how CSAIL researchers have unveiled a testing simulator for soft robotic designs. “It offers some interesting insights into how compliant robots can adapt to different environmental changes,” writes Heater.
Writing for Popular Science, Sarah Scoles spotlights DAILy (Developing AI Literacy) initiative, a project by MIT researchers and students aimed at teaching middle schoolers “the technical, creative, and ethical implications of AI, taking them from building PB&Js to totally redesigning YouTube’s recommendation algorithm.”
Popular Science reporter Charlotte Hu writes that MIT researchers have simulated an environment in which socially-aware robots are able to choose whether they want to help or hinder one another, as part of an effort to help improve human-robot interactions. “If you look at the vast majority of what someone says during their day, it has to do with what other [people] want, what they think, getting what that person wants out of another [person],” explains research scientist Andrei Barbu. “And if you want to get to the point where you have a robot inside someone’s home, understanding social interactions is incredibly important.”
MIT researchers have developed a new machine learning system that can help robots learn to perform certain social interactions, reports Brian Heater for TechCrunch. “Researchers conducted tests in a simulated environment, to develop what they deemed ‘realistic and predictable’ interactions between robots,” writes Heater. “In the simulation, one robot watches another perform a task, attempts to determine the goal and then either attempts to help or hamper it in that task.”
Quanta Magazine reporter Thomas Lewton spotlights Prof. Janet Conrad’s work on MiniBooNE, a neutrino particle detector that was in operation from 2002 until 2019.
Using an integrative modeling technique, MIT researchers compared dozens of machine learning algorithms to brain scans as part of an effort to better understand how the brain processes language. The researchers found that “neural networks and computational science might, in fact, be critical tools in providing insight into the great mystery of how the brain processes information of all kinds,” writes Anna Blaustein for Scientific American.
TechCrunch reporter Brian Heater spotlights RFusion, a fully-integrated robotic arm developed by MIT researchers that “uses an RF antenna and camera mounted to an arm to find lost objects.”
Graduate student Joy Buolamwini speaks with Good Morning America about her work uncovering bias in AI systems and how beauty data can marginalize people of color. “We can’t have social justice without algorithmic justice,” says Buolamwini.
Bloomberg’s Janet Wu speaks with alumna Nan-Wei Gong PhD '13, co-founder of Figur8, an MIT startup applying AI to help diagnose musculoskeletal problems. “Figur8 is a tool that really brings lab experience into the field so everyone can quantify their musculoskeletal injuries,” says Gong. “We invented a wearable system that allows you to capture biomarkers of your musculoskeletal health and pinpoint injury through our AI algorithm.”
Nuria Oliver PhD ’00 speaks with Wired reporter Willem Marx about her work developing a data gathering system to help combat Covid-19 in Valencia, Spain. Olivier and her team developed “a powerful predictor that's been road-tested during a time of unprecedented strain, and continues to be used across Valencia," writes Marx. "They have also created a system that can suggest a small number of specific, effective pandemic-related policies or interventions that a government can make.”
Inside Science reporter Tom Metcalfe writes that MIT researchers have developed a new method for taking the Earth’s temperature by examining basaltic rocks, and used the method to create a model of the Earth's oceanic ridges. "We are constantly stressing how [plate] tectonics operated in the past," says postdoc Stephanie Brown Krein. "And so I think it's really important for us to be able to understand how tectonics are working in the present day.”