ConvChess CNN

Discussion of chess software programming and technical issues.

Moderators: hgm, Dann Corbit, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Post Reply
Posts: 930
Joined: Tue Mar 09, 2010 2:46 pm
Location: New York
Full name: Álvaro Begué (RuyDos)

Re: ConvChess CNN

Post by AlvaroBegue » Wed Mar 15, 2017 6:01 pm

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.

Posts: 31
Joined: Fri Nov 25, 2016 9:14 am
Location: Singapore

Re: ConvChess CNN

Post by bhamadicharef » Thu Mar 16, 2017 4:16 am

Very interesting topic, thank you for sharing

Post Reply