Probabilistic AI that knows how well it’s working
It’s more important than ever for artificial intelligence to estimate how accurately it is explaining data.
Brain and cognitive sciences
Training machines to learn more like humans do
Researchers identify a property that helps computer vision models learn to represent the visual world in a more stable, predictable way.
Bacterial injection system delivers proteins in mice and human cells
With further development, the programmable system could be used in a range of applications including gene and cancer therapies.
New insights into training dynamics of deep classifiers
MIT researchers uncover the structural properties and dynamics of deep classifiers, offering novel explanations for optimization, generalization, and approximation in deep networks.
MIT-Takeda Program heads into fourth year with crop of 10 new projects
The program leverages MIT’s research expertise and Takeda’s industrial know-how for research in artificial intelligence and medicine.
Automating the math for decision-making under uncertainty
A new tool brings the benefits of AI programming to a much broader class of problems.