Over the last few months, I’ve been working on a research project to develop personalized training tools for chess players. For this post, I’m just going to describe Maia, the framework developed last year which all of our code and Read more…
Summary For this project, I analyzed methods to model the aleatoric and epistemic uncertainty of a neural network model for predicting the amount of time that a human player will use for a given move in a chess position. Dataset Read more…
Summary For this project, I am comparing the abilities of Bayesian and non-Bayesian neural networks as a predictor for how much time a chess player will use to make their move in a certain chess position, taking into account the Read more…
Problem During a chess game, players are constantly making decisions and evaluating the current state to increase their odds of winning. The process of analyzing positions is a problem that AI has already achieved superhuman performance on, and the use Read more…
Introduction In my AI class this semester, we have a 3-part course project based on the Berkeley CS118 Pacman Project. The first part of this project was due last week, and we were asked to implement some straightforward search algorithms Read more…
In my last two posts, I gave brief overviews to two of the more established paradigms for chess engines, represented by Stockfish and AlphaZero. In this post, I will go over the latest engine on the block – Stockfish NNUE. Read more…
Last week, I wrote an article explaining the basics on traditional chess engines. Today, I will go over the new generation of chess engines, using neural networks instead of brute force evaluation. History For decades, neural networks were thought to Read more…
Over the next few posts, I’ll be writing a series on how chess engines work. This isn’t intended to be an authoritative, in-depth guide on engines, but just a quick summary on the different types of chess engines, and how Read more…
Update – July 20, 2023 I’ve written two more blog posts on the topic of Colloquial Tamil. The first is an update to this post with a few additional learning resources I’ve found as well as published Anki decks. The Read more…
For my final project in Data Mining, we were given a dataset, the Wisconsin Breast Cancer Database, and asked to apply five different types of models to the data: KNN, Decision Tree, Random Forest, Polynomial SVM, Gaussian SVM, and a Read more…