What's up in
Neural networks are famously incomprehensible, so Been Kim is developing a “translator for humans.”
A visual prank exposes an Achilles’ heel of computer vision systems: Unlike humans, they can’t do a double take.
Machine learning techniques are commonly based on how the visual system processes information. To beat their limitations, scientists are drawing inspiration from the sense of smell.
The theoretical computer scientist Constantinos Daskalakis has won the Rolf Nevanlinna Prize for explicating core questions in game theory and machine learning.
In the hunt for new fundamental particles, physicists have always had to make assumptions about how the particles will behave. New machine learning algorithms don’t.
Judea Pearl, a pioneering figure in artificial intelligence, argues that AI has been stuck in a decades-long rut. His prescription for progress? Teach machines to understand the question why.
Faced with a navigational challenge, neural networks spontaneously evolved units resembling the grid cells that help living animals find their way.
In new computer experiments, artificial-intelligence algorithms can tell the future of chaotic systems.
The computer scientist Barbara Engelhardt develops machine-learning models and methods to scour human genomes for the elusive causes and mechanisms of disease.