What's up in

computer science

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

Solution: ‘How to Win at Deep Learning’

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

To efficiently analyze a firehose of data, scientists first have to break big numbers into bits.
algorithms

Best-Ever Algorithm Found for Huge Streams of Data

To efficiently analyze a firehose of data, scientists first have to break big numbers into bits.

A new version of AlphaGo needed no human instruction to figure out how to clobber the best Go player in the world — itself.
Abstractions blog

Artificial Intelligence Learns to Learn Entirely on Its Own

A new version of AlphaGo needed no human instruction to figure out how to clobber the best Go player in the world — itself.

What happens when you increase the number of layers in an artificial neural network?
insights puzzle

How to Win at Deep Learning

What happens when you increase the number of layers in an artificial neural network?

The real-world version of the famous “traveling salesman problem” finally gets a good-enough solution.
Abstractions blog

One-Way Salesman Finds Fast Path Home

The real-world version of the famous “traveling salesman problem” finally gets a good-enough solution.

A new idea is helping to explain the puzzling success of today’s artificial-intelligence algorithms — and might also explain how human brains learn.
Wired to Learn: The Next AI

New Theory Cracks Open the Black Box of Deep Learning

A new idea is helping to explain the puzzling success of today’s artificial-intelligence algorithms — and might also explain how human brains learn.

A tiny self-organized mesh full of artificial synapses recalls its experiences and can solve simple problems. Its inventors hope it points the way to devices that match the brain’s energy-efficient computing prowess.
Wired to Learn: The Next AI

A Brain Built From Atomic Switches Can Learn

A tiny self-organized mesh full of artificial synapses recalls its experiences and can solve simple problems. Its inventors hope it points the way to devices that match the brain’s energy-efficient computing prowess.

Computer scientists are finding ways to code curiosity into intelligent machines.
Wired to Learn: The Next AI

Clever Machines Learn How to Be Curious

Computer scientists are finding ways to code curiosity into intelligent machines.