TalkChess.com

Another machine learning neural net applied to chess:

http://cs231n.stanford.edu/reports/ConvChess.pdf

https://github.com/BarakOshri/ConvChess

The paper reports they couldn't get learning to work with 5 layers. There are a couple of easy tricks that make learning 5 layers trivial: Careful initialization of weights and using skip connections (see the ResNet paper). Other useful tricks are batch normalization and weight normalization.

I have trained CNNs for go with 30 layers using just the first two tricks.

Very interesting topic, thank you for sharing