zhihanyang2022 Goto Github PK

academic

aevb-tutorial

Minimal VAE, Conditional VAE (CVAE), Gaussian Mixture VAE (GMVAE) and Variational RNN (VRNN) in PyTorch, trained on MNIST.

alpha-zero

Minimal AlphaZero in PyTorch, trained on Connect4 on a 6x6 board.

ant_repo

This repo implements the HIRO algorithm for Hierarchical Reinforcement Learning in the original environment using Tensorflow 2.

astar_maze_solver

Use the A* search algorithm to solve 2D mazes.

auto-keras-imageclassifier-tutorial

This repo is intended to serve as a reference for using Auto-Keras for your personal image dataset

awesome-deep-learning-papers

The most cited deep learning papers

banditnotebooks

Analysis notebooks for bandit research with Prof Anna at Carleton.

bayesian-mixture-of-gaussians

Numpy code for Coordinate Ascent Variational Inference for the Bayesian mixture of Gaussians model (Sec 10.2 of Bishop's PRML).

bishop-pattern-recognition-notes

Contain Jupyter notebooks deriving, visualizing and understanding formulas found in Pattern Recognition by Bishop.

bishop1995-demos

bishop1995_notes

My notes and demos for understanding Neural Networks for Pattern Recognition (Bishop, 1995).

blog

blogs

Repository for content, code and other related materials for the blogs

classic_rl

A modular implementation of tabular RL algorithms.

cnn-experiments

Code for the project. Under Construction.

cnnvis

A Python library for visualizing convolutional neural networks.

code-examples

Code snippets from different languages.

cql

Code for conservative Q-learning

cql_modified

Investigation of potential modifications for CQL.

cs312

Homework for CS312 Audio Programming.

cv

Zhihan Yang's CV

d4rl

A benchmark for offline reinforcement learning.

d4rl_evaluations

Modification of the original d4rl_evaluations repo for experimentation.

dcase2018_task2_cochlearai

Cochlear.ai submission for dcase2018 task2

dcase_task2

Training General-Purpose Audio Tagging Networks with Noisy Labels and Iterative Self-Verification

deep-bayes-summer2022

Slides and notes of Bayesian + Deep Learning paper read during Summer 2022

deep-learning-performance

Experiments and results on tricks that speedup deep learning.

deeprl_notes

Demos of deep RL algorithms.

dior

Differentiable reparameterization of matrices with orthogonal columns.