deep learning

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

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

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.

With the help of deep learning techniques, paleoanthropologists find evidence of long-lost branches on the human family tree.

A visual prank exposes an Achilles’ heel of computer vision systems: Unlike humans, they can’t do a double take.

A controversial theory suggests that perception, motor control, memory and other brain functions all depend on comparisons between ongoing actual experiences and the brain’s modeled expectations.

The latest artificial intelligence systems start from zero knowledge of a game and grow to world-beating in a matter of hours. But researchers are struggling to apply these systems beyond the arcade.

When equipped with hidden layers, deep neural networks can accomplish nonlinear feats that are difficult even with sophisticated mathematics.