For the past few weeks (in addition to the school grind), I’ve been improving my Java Machine Learning library. After a few weeks of learning from online blog posts and papers, I have completed an overhaul of the existing code and I’ve added support for convolutional layers and GRU recurrent layers.
Recently, I’ve been working on some reinforcement learning. I learned about DDDQNs, which are neural networks that learns how to play games. Continue reading “Double Dueling DQN with Prioritized Experience Replay”
Around 2-3 weeks ago, I decided to create my own programming language and to write an interpreter for it in Java. Now, after fixing many bugs, the interpreter and the language documentation is finally finished. The whole project, called reCall, is available here, on GitHub. The whole experience was very interesting because I looked at many other programming language (even esoteric ones) and examined their syntax. Continue reading “Java Interpreter for reCall, a Programming Language”
Anyways, thanks for reading this short post!
This uses my neural network Java library that can be found here. The trained weights can also be found in the GitHub repository. Continue reading “Handwriting Recognition With MNIST Data in Java”
I’m starting to learn some Machine Learning (just learned Python). My first project is a simple machine learning addition program. Continue reading “Addition! (Python + Machine Learning)”
2D maze solver written in Java. Has a Swing GUI and it contains eight methods for solving mazes: BFS, DFS, Best-First BFS, Dijkstra’s, Bellman-Ford, Floyd-Warshall, A*, and simulate hand on right wall.