Skip to main content

Matthew - Capstone Blog Post 4



Finally, our CSI-480 (Advanced Topics: AI) course material is catching up to where we need to be. We are covering perceptrons and sigmoid neurons in the lectures, and we are also using TensorFlow to solve some very simple introductory problems (via tutorials). To supplement this I have been reading Neural Networks and Deep Learning by Michael Nielsen, a textbook available for free on the internet, which dives into neural networks right from the first chapter. Additionally, I have been finding 3Blue1Brown's multi-part video series about deep learning to be extremely helpful for visualizing some of the more advanced concepts. Even if I do not fully understand the calculus and linear algebra involved, at the very least I have a better idea of what goes on inside of neural networks. For example: I know what loss and gradient descent algorithms do, essentially, and I also understand how the latter helps find a local minimum for the former, but I do not necessarily feel confident in my understanding of the actual math behind them.

Overall, I feel like every step I take demystifies machine learning. Do my steps also deromanticize it? Perhaps a little. Somber piano music is playing on the radio, though, so take everything I say here with a grain of salt.

Before I let myself follow this train of thought any further, I really should think of our advisor, who I know would feel better if he saw some sign that we were working on our design document draft. And so, without any further ado, I hereby present our title page:

Note: Title pending review.

Should it be "the thrill of" or "the rush of"?
Anyway, never fear, for I have worked on more than just the title page!

Irrevocable proof that I installed a LaTeX compiler.
Fancy chart showing essentially the same content as the other screenshot.

And that is enough for one blog post. After all, every character I type here is a character I could be typing in the design document.

Labels

Labels:

Comments

Post a Comment

Popular posts from this blog

Matthew - Blog Post 7

Since January, we've been working hard to not only finish writing the Replay Parser and Frame Collector but also totally synchronize them. I'm pleased to report our success. This is an amazing milestone for us because it means that we've surmounted one of our most troubling obstacles. I have also made sure to keep our documentation up to date. So, if you like, you can follow along with this blog post by replicating its results. The Frame Collector uses timed input sequences to start each replay associated with the currently running game version. Then, after waiting a set amount of time for playback to begin, it starts grabbing 1/4-scale frames at a rate of 10 frames per second. The Frame Collector takes these down-scaled frames, which are NumPy arrays, and rapidly pickles and dumps them into the file system. Here's a screenshot of the Frame Collector in action: If you look at the image above, you'll see that each pickle (the .np files) ...
Post a Comment
Read more

Rei - Blog Post 10

So,  I missed blog post 9. This is me acknowledging that for consistency. Anyway, the past couple of weeks have been incredibly productive for ContentsMayBeHot. Matthew has finished collecting all the replay data, we have refactored our project to reduce complexity, we have improved the runtime of our code, and finally we have started seriously training our model. The Changes Matthew implemented multi-threading for the model loading. Which reduced our load time between files from about 3-5 Seconds to 1 Second or less. Which allows us to fully train a model in much less time! While Matthew did this I reduced the code duplication in our project. This way, if we needed to change how we loaded our training data, we didn't have to change it in multiple places. This just allows us to make hot-fixes much more efficiently. We also started working on some unittests for our project using pytest. These tests were written because of a requirement for another class, but we thought it...
Post a Comment
Read more

Rei - Blog Post 8

This most recent work period involved a lot of refactoring and adding some new key functionality. Matthew asked me to create a simplified Action Type in addition to the one that was all in place, basically just the same actions without PRESSED and RELEASED. Since we still wanted the original structure to be there, all I had to do was cast the "complex" actions to "simple actions. Matthew then asked if I could convert that SimpleAction type into a matrix, so we could have a clearly defined Y. This was also incredibly easy. I am actually quite happy with how it works as well. All you have to do to create an array for the action is two steps! matrix = numpy.zeros(26) if action is not SimpleAction.INVALID:     matrix[action] = 1; The 26 is the number of different Simple Actions we have. Then, to make it so we can run the parser separately from the Agent, I made it the replay can output numpy files for each character where each row in the file contains the frame of...
Post a Comment
Read more