Machine learning

If only scientists understood exactly how electrons act in molecules, they’d be able to predict the behavior of everything from experimental drugs to high-temperature superconductors. Following decades of physics-based insights, artificial intelligence systems are taking the next leap.

Two teams have shown how quantum approaches can solve problems faster than classical computers, bringing physics and computer science closer together.

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

In computer simulations of possible universes, researchers have discovered that a neural network can infer the amount of matter in a whole universe by studying just one of its galaxies.

Mathematicians and computer scientists answered major questions in topology, set theory and even physics, even as computers continued to grow more capable.

It’s simple enough for AI to seem to comprehend data, but devising a true test of a machine’s knowledge has proved difficult.

Tiny amounts of artificial noise can fool neural networks, but not humans. Some researchers are looking to neuroscience for a fix.

The computational biologist Anne Carpenter creates software that brings the power of machine learning to researchers seeking answers in mountains of cell images.

Algorithms that zero in on solutions to optimization problems are the beating heart of machine reasoning. New results reveal surprising limits.