neural networks

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.

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.

Researchers uncover striking parallels in the ways that humans and machine learning models acquire language skills.

In steganography, an ordinary message masks the presence of a secret communication. Humans can never do it perfectly, but a new study shows it’s possible for machines.

Today’s language models are more sophisticated than ever, but they still struggle with the concept of negation. That’s unlikely to change anytime soon.

Cynthia Rudin wants machine learning models, responsible for increasingly important decisions, to show their work.

By imbuing enormous vectors with semantic meaning, we can get machines to reason more abstractly — and efficiently — than before.