Anil Ananthaswamy

By apparently overtraining them, researchers have seen neural networks discover novel solutions to problems.

Far from being “stochastic parrots,” the biggest large language models seem to learn enough skills to understand the words they’re processing.

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

Diffusion models generate incredible images by learning to reverse the process that, among other things, causes ink to spread through water.

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.

By using hypernetworks, researchers can now preemptively fine-tune artificial neural networks, saving some of the time and expense of training.

Results from neural networks support the idea that brains are “prediction machines” — and that they work that way to conserve energy.

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

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.