I've been running training sessions for my latest model for roughly two months now and just getting frustrated. Progress is extremely slow, as the model is still infantile in its ability to play Gomoku. Looking at my adventures with Connect 4, the main things I learned are: Smaller training sets are fine as they are … Continue reading Slow Progress
I'm already facing up to the fact that the sheer amount of data in a game of Gobang / Gomoku / Connect 5 is quite a bit larger than in Connect 4; after all, the board is 15x15, where a Connect4 board is 7x6. 225 spaces on the board instead of 42 means you have … Continue reading A geometric explosion of data
The model I was training by only playing against me simply wasn't improving enough. A few thousand games in I realized how hopeless the idea of hand generating training data was, and gave up. I tried a new model, named Curly, which consisted of a single convolutional layer followed by a fully connected layer of … Continue reading I haven’t lost… quite.
So my current neural network I'm training, Larry, had previously increased his effectiveness to 90% against the SRP. Unfortunately, a few more dozen rounds decreased his effectiveness to the point that reverted to an 80% rating. That's unfortunate. On a lark, I started a new model on the side. This one was trained entirely by … Continue reading Reversion to the mean, and a new method