Machine learning

By bringing together disparate approaches, machines can reach a new level of creative problem-solving.

Alexei Efros has spent his career learning how machines see differently from humans. Now he’s helping to bridge the gap.

To better understand how neural networks learn to simulate writing, researchers trained simpler versions on synthetic children’s stories.

Some modern image generators rely on the principles of diffusion to create images. Alternatives based on the process behind the distribution of charged particles may yield even better results.

By using “classical shadows,” ordinary computers can beat quantum computers at the tricky task of understanding quantum behaviors.

Number theorist Andrew Granville on what mathematics really is — and why objectivity is never quite within reach.

Researchers have discovered ways around a fundamental trade-off between accuracy and beauty in digital images.

New results break with decades of conventional wisdom for the gradient descent algorithm.

Real data can be hard to get, so researchers are turning to synthetic data to train their artificial intelligence systems.