Anil Ananthaswamy

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.

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.

The result highlights a fundamental tension: Either the rules of quantum mechanics don’t always apply, or at least one basic assumption about reality must be wrong.

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

Pure, verifiable randomness is hard to come by. Two proposals show how to make quantum computers into randomness factories.

The Frauchiger-Renner thought experiment has shaken up the world of quantum foundations.