AlphaCode Attention Visualization. Hover over tokens in the solution to see which tokens the model attended to when generating the solution. Click a token to select it; clicking in empty space will deselect.

Explore how moves played by AlphaGo compare to those of professional and amateur players. This tool provides analysis of thousands of the most popular opening sequences from the recent history of Go, using data from 231,000 human games and 75 games that DeepMind's AlphaGo played against human players

Ithaca was conceived and researched by Yannis Assael*, Thea Sommerschield*, Brendan Shillingford, Mahyar Bordbar, John Pavlopoulos, Marita Chatzipanagiotou, Ion Androutsopoulos, Jonathan Prag, and Nando de Freitas. This web experience was developed and built on Google Cloud by Justin Grayston, Benjamin Maynard, and Ricardo Cardenas.

AlphaGo Fan 与樊麾的 5 盘对局 AlphaGo Lee 在 Google DeepMind 挑战赛与李世石的 5 盘对局 AlphaGo Master 的 60 盘网络对局 AlphaGo Master 在中国乌镇围棋峰会中的 5 盘对局; 此AlphaGo教学工具由黃士杰、樊麾和Lucas Baker共同研发。

알파고의 수들이 프로 및 아마 강자의 수들과 어떻게 다른지 알아보세요. 이 툴은 총 231,000판의 사람 간 대국과 딥마인드 알파고의 대국 75판을 분석해 선별한 가장 많이 두어진 포석 수 천가지의 연구 결과를 제공합니다

AlphaGo Fan 與樊麾的 5 盤對局 AlphaGo Lee 在 Google DeepMind 挑戰賽與李世石的 5 盤對局 AlphaGo Master 的 60 盤網路對局 AlphaGo Master 在中國烏鎮圍棋峰會中的 5 盤對局; 此AlphaGo教學工具由黃士傑、樊麾和Lucas Baker共同研發。

AlphaGo と棋士たちの手を比較してみましょう。このツールは、よくある序盤パターンを、人同士が打った 231,000 局と、DeepMind 開発の AlphaGo が人と対局した 75 局の棋譜データから分析することができます。

Our pioneering research includes Deep Learning, Reinforcement Learning, Theory & Foundations, Neuroscience, Unsupervised Learning & Generative Models, Control & Robotics, and Safety.