AlphaGo

The 1st Computer Program to Defeat a GO Game World Champion

---

Screenshots

View Image	View Image	View Image	View Image

---

Hunter's comment

Go is an ancient chinese board game with more possible moves than no of atoms in Universe.
Tradition AIs using Brute force mode to anticipate ahead all possible moves, stand no chance in the Game of Go.

AlphaGo created a turmoil in the world of AI when it defeated the World Champion Lee Sedol.

It uses reinforcement learning, in which becomes its own teacher. The system starts off with a neural network that knows nothing about the game of Go. It then plays games against itself, by combining this neural network with a powerful search algorithm. As it plays, the neural network is tuned and updated to predict moves intuitively like humans.

This is intuitive leaning just like humans.

Imagine what AlphaGo can do in fields health, environment and technology etc, This may one day solve the mankind's big unsolved problems.

---

Link

https://deepmind.com/research/alphago/

---

Contributors

Hunter: @xabi

---

This is posted on Steemhunt - A place where you can dig products and earn STEEM.
View on Steemhunt.com