TomBolton.io

Tom Bolton’s AI and Machine Learning Lab Notebook.

Machine Learning

Machine Learning

Back when I first read Andrej Karpathy’s revelatory Deep Reinforcement Learning: Pong from Pixels and wrote about it back in this post, I saw that he kept referring to the log probability of any given movement rather than the actual probability….

Machine Learning

It’s been a while since I posted anything here. In addition to doubling up on my AI course load, I’ve been doing some work on the side for a colleague who’s VP of Development for an AI startup that does…

Machine LearningVideo Games

Last night, after working some more on my checkers algorithm, before going to bed I decided to unwind by playing a little Destiny 2. With checkers and Destiny 2 on my brain, I had a dream in which I was…

Machine Learning

Andrej Karpathy’s Pong from Pixels has been my exemplar for implementing reinforcement learning. I find that in general, I’m following along with his approach, and I feel that conceptually, it’s making sense. But as I set out to actually create my…

Machine Learning

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…

Machine Learning

It’s been a while since I wrote about my checkers project. For a few weeks there, I was able to give it a lot of consideration because I was doing the first course in the Deep Learning specialization, Deep Neural…

Machine Learning

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…

Machine Learning

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…

Machine Learning

I’ve begun in earnest to build the Checkers AI, and right now for the most part that means plumbing. Before I even get to how this NN is going to work, I need to have the framework in place that…

Machine Learning

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…