Neural networks

Artificial intelligence learned how to generate text and art better than ever before, while computer scientists developed algorithms that solved long-standing problems.

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

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.

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

New research finds that the memories useful for future generalizations are held in the brain separately from those recording unusual events.

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

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

A novel type of neural network is helping physicists with the daunting challenge of data analysis.