Zhongxia Yan's Projects
Multiprocess implementation of Alphazero applied to the board game Gomoku (五子棋; 5 in a row; tic-tac-toe but with 5 pieces on a 20x20 board)
Has no name yet. An AR app that simulates an instruction
A customizable, multilayered, and fully Numpy-parallelized/cythonized (convolutional) neural network classifier.
Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://nervanasystems.github.io/distiller
Code and model for the paper "Improving Language Understanding by Generative Pre-Training"
Computational framework for reinforcement learning in traffic control
A website for managing finances in our house
Some Chrome Extensions and other programs.
[ITSC 2021] Reinforcement Learning for Mixed Autonomy Intersections
Team repo for ML@B Unity Delighting project
[PMLR'20] NeurIPS 2019 MicroNet Challenge Efficient Language Modeling, Champion
Open source Structure from Motion pipeline
Python AI template for Piskvork gomoku manager
Perform Model Checking and POMDP Planning from LTL specifications using POMDPs.jl
Solutions to Project Euler, a series of computational questions online. See the problems here: https://projecteuler.net/
A fast and simple framework for building and running distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
A tensorflow implementation for SqueezeDet, a convolutional neural network for object detection.
Ternary Weight Pruning for SqueezeDet
Eclipse SUMO is an open source, highly portable, microscopic and continuous traffic simulation package designed to handle large networks. It allows for intermodal simulation including pedestrians and comes with a large set of tools for scenario creation.
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.