[Computer-go] Fwd: Teaching Deep Convolutional Neural Networks to Play Go

[hughperkins2]

> The important thing is that the games don't have to be played perfectly: They just need to be significantly better than your current model, so you can tweak the model to learn from them.

Thats an important incite. I hadnt thought of that. 

Maybe could combine with some concept of "forgetting", eg weight decay, so the net gradually unlearns some of the original, more naive, associations? > The important thing is that the games don't have to be played perfectly: They just need to be significantly better than your current model, so you can tweak the model to learn from them.

Thats an important incite. I hadnt thought of that. 

Maybe could combine with some concept of "forgetting", eg weight decay, so the net gradually unlearns some of the original, more naive, associations? could combine with some concept of "forgetting", eg weight decay, so the net gradually unlearns some of the original, more naive, associations? 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://computer-go.org/pipermail/computer-go/attachments/20150316/ea6961c7/attachment.html>