When computer vision works more like a brain, it sees more like people do
Training artificial neural networks with data from real brains can make computer vision more robust.
McGovern Institute
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.