AlphaGo

AI Google Science

800 YEARS OF DISCOVERY IN 17 DAYS!! How will ‘GNOME’ CHANGE THE WORLD

This video is from The AI Wave. Artificial intelligence has advanced by leaps and bounds in recent years, and Google’s DeepMind has been at the forefront of this revolution. One of their latest accomplishments is the development of GnoME AI, a new tool that utilizes deep learning to significantly accelerate the process of discovering new […]

Read More
AI Bioinformatics

AlphaFold: The making of a scientific breakthrough

Here is the inside story of the DeepMind team of scientists and engineers who created AlphaFold, an AI system that is recognized as a solution to “protein folding”, a grand scientific challenge for more than 50 years.

Read More
AI Reinforcement Learning

DeepMind’s New AI MuZero Mastered More Than 50 Games

Two Minute Papers explores the paper “Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model.”

Read More
AI Reinforcement Learning

DeepMind’s AlphaStar: A Grandmaster Level StarCraft 2 AI

Two Minute Papers explores the paper “AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning” in this video. 

Read More
Reinforcement learning explained
Reinforcement Learning TensorFlow

Reinforcement learning explained

Here’s a great explanation of Reinforcement Learning, AlphaGo Zero, and how it compares to other forms of machine learning. For example, AlphaGo, in order to learn to play (the action) the game of Go (the environment), first learned to mimic human Go players from a large data set of historical games (apprentice learning). It then […]

Read More
AI Reinforcement Learning

How Deepmind’s AlphaZero Can Master Games Without Human Knowledge

If my post yesterday about DeepMind’s AlphaZero piqued your interest but answered too few questions, then check out this video from teh 2017 NIPS conference where Dr. David Silver delivers the keynote. Dr. David Silver leads the reinforcement learning research group at DeepMind and is lead researcher on AlphaGo.

Read More
Deep Learning Reinforcement Learning

How AlphaGo Zero Taught Itself to Be a Go Master

First, AlphaGo beat the best human player in the world by studying thousands of human vs. human games. Then AlphaGo Zero came along and taught itself to be even better without any human generated data. By the way, it beat AlphaGo. This is the power of Reinforcement Learning.

Read More