Machine learning

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.

Physicists are building neural networks out of vibrations, voltages and lasers, arguing that the future of computing lies in exploiting the universe’s complex physical behaviors.

Researchers say we’re on the cusp of “GoPro physics,” where a camera can point at an event and an algorithm can identify the underlying physics equation.

Language processing programs are notoriously hard to interpret, but smaller versions can provide important insights into how they work.

For centuries, mathematicians have tried to prove that Euler’s fluid equations can produce nonsensical answers. A new approach to machine learning has researchers betting that “blowup” is near.

Traditional algorithms power complicated computational tools like machine learning. A new approach, called algorithms with predictions, uses the power of machine learning to improve algorithms.