artificial intelligence

A new model of learning centers on bursts of neural activity that act as teaching signals — approximating backpropagation, the algorithm behind learning in AI.

To help them explain the shocking success of deep neural networks, researchers are turning to older but better-understood models of machine learning.

Computational neuroscientists taught an artificial neural network to imitate a biological neuron. The result offers a new way to think about the complexity of single brain cells.

Melanie Mitchell has worked on digital minds for decades. She says they’ll never truly be like ours until they can make analogies.

Two new approaches allow deep neural networks to solve entire families of partial differential equations, making it easier to model complicated systems and to do so orders of magnitude faster.

Rediet Abebe uses the tools of theoretical computer science to understand pressing social problems — and try to fix them.

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.

Deep neural networks, often criticized as “black boxes,” are helping neuroscientists understand the organization of living brains.

To tame urban traffic, the computer scientist Carlos Gershenson finds that letting transportation systems adapt and self-organize often works better than trying to predict and control them.