ÉtudeScience

Computer Science & AI · 2016

Mastering the Game of Go with Deep Neural Networks and Tree Search

David Silver, Aja Huang, et al. (DeepMind)

Google DeepMind

Nature, vol. 529, pp. 484–489 ·

Cited by 19,000+Open access
View original paper

Opens the version of record via DOI

AlphaGo became the first program to beat a professional human at the ancient board game Go, long considered a grand challenge for AI because of its astronomical complexity. It combined deep neural networks with Monte Carlo tree search.

Showed AI could master intuition-heavy domains; AlphaGo beat Lee Sedol months later.

  • Defeated a professional human Go player on a full-size board — a milestone thought to be years away.
  • Used 'policy' and 'value' neural networks to guide and evaluate moves.
  • Combined deep learning with Monte Carlo tree search and reinforcement learning from self-play.

Neural networks were trained first on expert human games then improved by reinforcement learning through self-play; at play time they guided a Monte Carlo tree search that selected moves.

Keywords

Computer Science & AI

Highly Accurate Protein Structure Prediction with AlphaFold

Jumper et al. · 2021 · Nature

AlphaFold solved a 50-year grand challenge in biology: predicting a protein's three-dimensional shape from its amino-acid sequence. Its accuracy approached that of experimental methods, transforming structural biology.

Cited by 37,000+Open access

Computer Science & AI

Attention Is All You Need

Vaswani et al. · 2017 · Advances in Neural Information Processing Systems (NeurIPS)

The paper that introduced the Transformer, an architecture built entirely on attention mechanisms with no recurrence or convolution. It became the foundation of modern large language models such as GPT and BERT.

Cited by 180,000+Open access

Computer Science & AI

Deep Learning

LeCun, Bengio & Hinton · 2015 · Nature

A landmark review by three pioneers of the field, synthesising how deep neural networks learn layered representations of data. It explains why depth works and surveys the advances that made deep learning dominant across vision, speech, and language.

Cited by 110,000+

Étude Science indexes and summarises this work; it is not the publisher. The summary above is written by Étude. For the definitive text, figures, and data, please consult the original publication via the link above. Silver et al. (2016) hold the rights to the original work.