Even networks long considered "untrainable" can learn effectively with a bit of a helping hand. Researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have shown that a ...

Real data can be hard to get, so researchers are turning to synthetic data to train their artificial intelligence systems. On a sunny day in late 1987, a Chevy van drove down a curvy wooded path on ...

This is a graduate topics course on learning in networks, focusing in particular on fundamental statistical and computational limits. Topics include the planted clique problem, community detection, ...

The learning algorithm that enables the runaway success of deep neural networks doesn’t work in biological brains, but researchers are finding alternatives that could. In 2007, some of the leading ...