David J Wu

About those features in the global pooling - I have no idea! But when you look at the activation patterns in real board positions, the neural net is very clearly...

Some further thoughts: note that these features are all "different" in various ways that I didn't summarize, because despite seeing that they looked "different" it was hard to say exactly...

I have some ideas about how to do it, but I'm not really personally excited about trying to handcraft weights in a neural net. :) Right now I'm experimenting with...

@tapsika - right, 16*16*19*19*19*19 is a very large number of parameters, and provides massive opportunity for the neural net to underfit. Underfitting would be expected because without the strong prior...

Thanks! I will take a look. :)

Whee! I just pushed a bunch of stuff and finished editing the readme to add notes about all many more of experiments I've been running over the last two months....

Not sure. Any thoughts on what experiments or stats might tease out further aspects of this? I've looked at heatmaps of what some of the internal layers are computing, and...

Updated results! @killerducky - I tried dilated convolutions and added notes about them, along with various other updated notes and results! They add a very slight cost to the neural...

I think factors of 2 or 3 are okay, but as you go beyond that I think it's probably harder for the neural net to be accurate about connectivity. So...

Posted some minor updates. In other news, as a result of the experimentation in this repo, I have a new site up! https://neuralnetgoproblems.com