Meet The Father Of AlphaGo: AlphaGo Zero

David Fumo
Nov 10, 2017 · 3 min read

Google’s New AlphaGo Breakthrough Could Take Algorithms Where No Humans Have Gone, ‘It’s able to create knowledge itself’.

“The time when humans can have a meaningful conversation with an AI has always seemed far off and the stuff of science fiction. But for Go players, that day is here.”- Nick Hynes

While it sounds like some sort of soda, AlphaGo Zero may represent as much of a breakthrough as its predecessor, since it could presage the development of algorithms with skills that humans do not have and others go far and say that this Stunning AI Breakthrough Takes Us One Step Closer to the Singularity, I think is still early to tell how this can take us and Intelligence is not solved yet.

“It’s like an alien civilization inventing its own mathematics which allows it to do things like time travel…Although we’re still far from ‘The Singularity,’ we’re definitely heading in that direction.” — Nick Hynes

Mastering the game of Go without human knowledge

AlphaGo is the first computer program which had itself defeated 18-time world champion Lee Sedol at Go, an ancient and complex Chinese board game of strategy and intuition which many believed could never be cracked by a machine. Google DeepMind states that AlphaGo Zero is even more powerful and is arguably the strongest Go player in history.

Previous versions of AlphaGo initially trained on thousands of human amateur and professional games to learn how to play Go. AlphaGo Zero skips this step and learns to play simply by playing games against itself, starting from completely random play.

What makes AlphaGo special?

— Beat the previous version of AlphaGo (Final score: 100–0).

— Learned to play Go from scratch, without learning from previous human knowledge.

— Achieved world-champion level Go playing in just 3 days of training.

— Did so with an order of magnitude less neural networks ( 4 TPUs vs 48 TPUs).

— Did this with less training data (3.9 million gaanmes vs 30 millions games).

Training Time

source: DeepMind

Computing Power

Hardware Usage

source: DeepMind

AlphaGo Zero comes as a reminder that there is still more to be done in Artificial Intelligence and Google DeepMind once again showed their majesty and skills applying reinforcement learning, the algorithm in which AlphaGo Zero becomes its own teacher.

source: DeepMind

References

Before you go!

In the AI world there are a lot of terminologies and it’s easy to get lost in a conversation, reading or thinking that those terms comes from mars, I felt this myself when I started learning Machine Learning, if you feel this way too, I recommend you to read Artificial Intelligence terminologies written by Richaldo Elias and get yourself comfortable with those buzzwords, have fun.

If you enjoyed this post leave your claps 👏 to recommend this article so that others can see it.

With ❤ by J. David Fumo!

May The Force Be With You!

David Fumo

Written by

love coding, read, write and create. Interested in AI, Blockchain, Startups, Growth and Entrepreneurship.

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade