top of page

Deep Learning: AlphaGo Zero Explained In One Picture

  • L.V.
  • Jan 7, 2018
  • 1 min read

Recently Google DeepMind announced AlphaGo Zero — an extraordinary achievement that has shown how it is possible to train an agent to a superhuman level in the highly complex and challenging domain of Go, ‘tabula rasa’ — that is, from a blank slate, with no human expert play used as training data.

It thrashed the previous reincarnation 100–0, using only 4TPUs instead of 48TPUs and a single neural network instead of two.

Some opinions expressed in this article may be those of a guest author and not necessarily Analytikus. Staff authors are listed https://www.datasciencecentral.com/profiles/blogs/deep-learning-alphago-zero-explained-in-one-picture

 
 

POST

USA

SPAIN

MEXICO

© 2025 by analytikus, LLC  - Privacy Policy

United States

  • LinkedIn
  • Twitter
  • Youtube
  • Spotify
Microsoft Gold. Partner
Badge Microsoft Partner Pledge
OEA Microsoft Advanced Partnerng
Endeavor Education Award
GESA Education Award
HOLONIQ Award 2020

Disclaimer: The products and solutions presented on this website are at different stages of development, ranging from conceptualization and research to experimental phases, pilot programs with educational institutions, and full-scale production deployments. Analytikus continuously works on the evolution and enhancement of its technologies, meaning that some features may still be under development or adaptation to meet the needs of the education sector.

bottom of page