Page 1 of 1

Re: ConvChess CNN

Posted: Wed Mar 15, 2017 6:01 pm
by AlvaroBegue
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.

Re: ConvChess CNN

Posted: Thu Mar 16, 2017 4:16 am
by bhamadicharef
Very interesting topic, thank you for sharing