What's up in
Neural networks
Latest Articles
Playing Hide-and-Seek, Machines Invent New Tools
After millions of games, machine learning algorithms found creative solutions and unexpected new strategies that could transfer to the real world.
Computers Evolve a New Path Toward Human Intelligence
By ignoring their goals, evolutionary algorithms have solved longstanding challenges in artificial intelligence.
A Power Law Keeps the Brain’s Perceptions Balanced
Researchers have discovered a surprising mathematical relationship in the brain’s representations of sensory information, with possible applications to AI research.
Machines Beat Humans on a Reading Test. But Do They Understand?
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.
Computers and Humans ‘See’ Differently. Does It Matter?
In some ways, machine vision is superior to human vision. In other ways, it may never catch up.
A Mathematical Model Unlocks the Secrets of Vision
Mathematicians and neuroscientists have created the first anatomically accurate model that explains how vision is possible.
His Artificial Intelligence Sees Inside Living Cells
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.
Where We See Shapes, AI Sees Textures
To researchers’ surprise, deep learning vision algorithms often fail at classifying images because they mostly take cues from textures, not shapes.
Do Brains Operate at a Tipping Point? New Clues and Complications
New experimental results simultaneously advance and challenge the theory that the brain’s network of neurons balances on the knife-edge between two phases.