neural networks

By ignoring their goals, evolutionary algorithms have solved longstanding challenges in artificial intelligence.

Researchers have discovered a surprising mathematical relationship in the brain’s representations of sensory information, with possible applications to AI research.

A tool known as BERT can now beat humans on advanced reading-comprehension tests. But it’s also revealed how far AI has to go.

In some ways, machine vision is superior to human vision. In other ways, it may never catch up.

Mathematicians and neuroscientists have created the first anatomically accurate model that explains how vision is possible.

The computer vision scientist Greg Johnson is building systems that can recognize organelles on sight and show the dynamics of living cells more clearly than microscopy can.

To researchers’ surprise, deep learning vision algorithms often fail at classifying images because they mostly take cues from textures, not shapes.

New experimental results simultaneously advance and challenge the theory that the brain’s network of neurons balances on the knife-edge between two phases.

The latest AI algorithms are probing the evolution of galaxies, calculating quantum wave functions, discovering new chemical compounds and more. Is there anything that scientists do that can’t be automated?