TomBolton.io

Tom Bolton’s AI and Machine Learning Lab Notebook.

Machine Learning

Measuring Success, Part 1

So with these classifiers and unambiguous accuracy numbers when compared to ground truth, it’s dead simple to evaluate success. But what about this checkers game? Unlike the pong from pixels example, my game won’t be playing against a functioning, trained…

A Revelation

My personal experience with Neural Networks is that everything became much clearer when I started ignoring full-page, dense derivations of backpropagation equations and just started writing code…(I don’t believe [a lot of math] is necessary and it can sometimes even…

Half Measures or Full Measures?

Yesterday, I put some of the plumbing in place to eventually run a checkers game for one or two AIs. Specifically, the board is represented, the fundamentals of pieces are represented, and the system has a way, for any given…

A Tiny Victory

The one thing that was disappointing in the results of the Python Port of my NN was the time it took to learn the training set. I wasn’t sure what the reason was, and had speculated that it might have…

Planning Checkers

As I mentioned, my checkers-playing AI is on hold until I have a few more viable tools available to do what’s necessary. However, since no matter what I do, I can’t stop thinking about the problem, it occurs to me…

Taking a Step Back

In addition to coursework and reading, I’ve continued to think about checkers—because it seems both challenging and tractable, and I have the basic domain knowledge. These supports two main short term goals for the next 6 months or so. The…

Thoughts on Checkers

A while ago, at the time when I was (ludicrously, it seems) considering tic tac toe as a viable candidate for an AI project, it occurred to me that Checkers was a probably a better candidate. I don’t actually play games…