Page 1 of 1
ConvChess CNN
Posted: Wed Mar 15, 2017 6:33 pm
by brianr
Re: ConvChess CNN
Posted: Wed Mar 15, 2017 7:01 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 5:16 am
by bhamadicharef
Very interesting topic, thank you for sharing