deep learning

Inspired by the results of a game-playing neural network, mathematicians have been making unexpected advances on an age-old math problem.

An energy-efficient chip called NeuRRAM fixes an old design flaw to run large-scale AI algorithms on smaller devices, reaching the same accuracy as wasteful digital computers.

Neural networks originally designed for language processing turn out to be great models of how our brains understand places.

Anima Anandkumar wants computer scientists to move beyond the matrix, among other challenges.

Self-supervised learning allows a neural network to figure out for itself what matters. The process might be what makes our own brains so successful.

Christopher Kanan is building algorithms that can continuously learn over time — the way we do.

Intelligent beings learn by interacting with the world. Artificial intelligence researchers have adopted a similar strategy to teach their virtual agents new tricks.

A simple algorithm that revolutionizes how neural networks approach language is now taking on image classification as well. It may not stop there.

Algorithms that use the brain’s communication signal can now work on analog neuromorphic chips, which closely mimic our energy-efficient brains.