In machine learning, synthetic data can offer real performance improvements
Models trained on synthetic data can be more accurate than other models in some cases, which could eliminate some privacy, copyright, and ethical concerns from using real data.
Nanosensors target enzymes to monitor and study cancer
By analyzing enzyme activity at the organism, tissue, and cellular scales, new sensors could provide new tools to clinicians and cancer researchers.
Methane research takes on new urgency at MIT
Desiree Plata's research focuses on developing technologies and strategies for environmental sustainability.
A new control system for synthetic genes
Researchers have developed a technique that could help fine-tune the production of monoclonal antibodies and other useful proteins.
Using sound to model the world
This machine-learning system can simulate how a listener would hear a sound from any point in a room.
Machine learning facilitates “turbulence tracking” in fusion reactors
A new approach sheds light on the behavior of turbulent structures that can affect the energy generated during fusion reactions, with implications for reactor design.
Ashton Carter, former U.S. secretary of defense who served in leadership roles at the MIT Corporation and Lincoln Laboratory, dies at 68
A trained theoretical physicist, Carter devoted his wide-ranging knowledge to government service.
A better way to tell which species are vulnerable
New analysis takes account of natural fluctuations and predictability to assess which parts of an ecosystem are most threatened by climate change and other disruptions.
Angela Koehler takes on the most challenging drug targets
Using biological, chemical, and engineering tools, she has developed strategies to attack molecules once thought to be “undruggable.”
Helping blockchain communities fix bugs
MIT alumnus-founded Metrika has developed a suite of analytics tools giving blockchain communities visibility into their networks.