What's up in
Self-Taught AI Shows Similarities to How the Brain Works
Self-supervised learning allows a neural network to figure out for itself what matters. The process might be what makes our own brains so successful.
The Computer Scientist Challenging AI to Learn Better
Christopher Kanan is building algorithms that can continuously learn over time — the way we do.
Computer Science Proof Unveils Unexpected Form of Entanglement
Three computer scientists have posted a proof of the NLTS conjecture, showing that systems of entangled particles can remain difficult to analyze even away from extremes.
The Scientist Who Developed a New Way to Understand Communication
Mark Braverman has spent his career translating thorny problems into the language of information complexity.
By Exploring Virtual Worlds, AI Learns in New Ways
Intelligent beings learn by interacting with the world. Artificial intelligence researchers have adopted a similar strategy to teach their virtual agents new tricks.
The Computer Scientist Who Parlays Failures Into Breakthroughs
Daniel Spielman solves important problems by thinking hard — about other questions.
Researchers Achieve ‘Absurdly Fast’ Algorithm for Network Flow
Computer scientists can now solve a decades-old problem in practically the time it takes to write it down.