TomBolton.io

Tom Bolton’s AI and Machine Learning Lab Notebook.

Machine Learning

The Refactoring Grind

I’ve been making slow progress on refactoring my code to play checkers in parallel. In fact, it’s not merely to play in parallel, but in fact, more like simultaneously. Parallel implies that games going on simultaneously have nothing to do…

Refactoring Checkers

It’s a new year. I’m too busy, but now that the holiday craziness is over it’s time to hunker down and do what I decided: refactor my home-grown checkers game-playing mechanics to play games in parallel rather than sequentially. It…

Tensorflow, *sigh*

I started a new job running product for an AI startup, and it’s been pretty intense, not leaving much time to do my big TensorFlow conversion. But over the last week, I got back to it, and yesterday I got…

Moving On

It’s been an eventful few days for my model. This entry is going to be a bit of a saga, but here goes. I had implemented the weighting function as described in my last post. I was getting great results…

Actually, Not Tricky at All

Okay. Last post I wrote that it’s tricky to do a non-simplistic naive implementation of taking into account all the attempts. Actually, though, it’s not tricky at all, and when I originally thought about it weeks ago, I was so…

True Cost

It’s been a while since I posted anything here, and in fact, a good while since I worked on this project. Shortly after my last post, school started for the boys, and that’s always a bit of a transition. Also,…

Inexplicable Results Explained

Built a quick (slow) framework to track board state and proposed illegal and legal moves for every game, and save out the game history for any game where the illegal move percentage spiked to higher than 98%. The vast majority…

Inexplicable Results

So, with my new softmax back propagation sorted, I was excited to see how my model would perform, especially since softmax with MSE was my first hypothesis. Well, MSE was a disaster, although I didn’t push it too far. Softmax with…