Researchers from MIT and Caltech have developed a pill-shaped ingestible sensor that can be monitored as it moves through the GI tract, allowing doctors to more easily diagnose gastrointestinal disorders, reports Brian Heater for TechCrunch. “The ability to characterize motility without the need for radiation, or more invasive placement of devices, I think will lower the barrier for people to be evaluated,” says Prof. Giovanni Traverso.
Motherboard reporter Tatyana Woodall writes that a new study co-authored by MIT researchers finds that AI models that can learn to perform new tasks from just a few examples create smaller models inside themselves to achieve these new tasks. “Learning is entangled with [existing] knowledge,” graduate student Ekin Akyürek explains. “We show that it is possible for these models to learn from examples on the fly without any parameter update we apply to the model.”
Researchers at MIT and Massachusetts General Hospital have developed “Sybil” – an artificial intelligence tool that can predict the risk of a patient developing lung cancer within six years, reports Mallika Marshall for CBS Boston.
Prof. Sara Seager and her colleagues write for Physics Today about how the SpaceX Starship could help transform astrophysics missions. “Assuming it is successful, Starship will dramatically enhance our space capabilities in ways that will qualitatively alter how astrophysics missions can be built,” write Seager and her colleagues.
Visiting scientist Judah Cohen speaks with Boston.com reporter Eli Curwin about how a combination of more accurate data collection, precise weather models, and accessible forecast predictions make it unlikely that Massachusetts residents would be surprised again by a storm like the infamous Blizzard of ‘78. “The satellites, the ships, the weather stations, weather balloons used to integrate and assimilate all that data are much better than they used to be,” says Cohen.
Prof. Daniela Rus, director of CSAIL, speaks with Popular Science reporter Charlotte Hu about the field of artificial intelligence, explaining the difference between AI, robotics and machine learning, and exploring the future of AI. “[AI algorithms] can do really extraordinary things much faster than we can. But the way to think about it is that they’re tools that are supposed to augment and enhance how we operate,” says Rus. “And like any other tools, these solutions are not inherently good or bad. They are what we choose to do with them.”
Research scientist Mary Knapp and her collaborators are working on a concept for The Great Observatory for Long Wavelengths (Go-LoW), a space-based observatory comprised of small satellites aimed at making low-frequency radio waves visible, reports Ashley Strickland for CNN. “I learned back in my undergrad days that there was this part of the spectrum we couldn’t see,” Knapp explains. “It really just struck me that there was this unexplored part of the universe, and I want to explore this part of the sky for the first time.”
Researchers at MIT have discovered what makes ancient Roman concrete “exponentially more durable than modern concrete,” reports Jim Morrison for Wired. “Creating a modern equivalent that lasts longer than existing materials could reduce climate emissions and become a key component of resilient infrastructure,” writes Morrison.
MIT researchers devised a new way to arrange LED pixels to create screens with a much higher resolution than is currently possible, reports The Economist. The new technique, which involves stacking micro LEDS, could also be used to make “VR images that appear far more lifelike than today’s.”
Researchers at MIT have developed an autonomous vehicle with “mini sensors to allow it to see the world and also with an artificially intelligent computer brain that can allow it to drive,” explains postdoctoral associate Alexander Amini in an interview with Mashable. “Our autonomous vehicles are able to learn directly from humans how to drive a car so they can be deployed and interact in brand new environments that they’ve never seen before,” Amini notes.
MIT researchers have developed a new AI tool called Sybil that could help predict whether a patient will get lung cancer up to six years in advance, reports Pranshu Verma for The Washington Post. “Much of the technology involves analyzing large troves of medical scans, data sets or images, then feeding them into complex artificial intelligence software,” Verma explains. “From there, computers are trained to spot images of tumors or other abnormalities.”
An MIT study has found that the wide spread adoption of self-driving cars could lead to increased carbon emissions, reports Rima Sabina Aouf for Dezeen. “The study found that with a mass global take up of autonomous vehicles, the powerful onboard computers needed to run them could generate as many greenhouse gas emissions as all the data centers in operation today,” writes Aouf.
Researchers at MIT developed SoFi, a soft robotic fish designed to study underwater organisms and their environments, reports Mashable. “The soft robotic fish serves a nice purpose for hopefully minimizing impact on the environments that we’re studying and also helps us study different types of behaviors and also study the actual mechanics of these organisms as well,” says graduate student Levi Cai.
President Sally Kornbluth, Provost Cynthia Barnhart, and Chancellor Melissa Nobles speak with Radio Boston host Tiziana Dearing about the importance of representation for women and underrepresented groups in STEM. “One of the most important pieces of having women in leadership is not just bringing a diverse perspective, but honestly being role models so that girls see that there is a possibility for them to be doing the kind of high-tech, heavy research that MIT does,” says Kornbluth.
Forbes reporter Jeff McMahon spotlights visiting scientist Judah Cohen for his research examining the connection between Arctic snow cover and sea ice to cold air intrusions in the United States during the month of February. “December has certainly been warming if you look at the U.S.,” sayscCohen. But “February, going back to 1979—so quite a few years now—we're actually seeing in the center of the U.S. a very distinctive cooling trend.”