Lei Mao
Machine Learning, Artificial Intelligence, Computer Science.
Twitter Facebook LinkedIn GitHub G. Scholar E-Mail RSSArticles
2019
RSA Algorithm
Posted: November 10, 2019 Updated: November 10, 2019
A Self-Contained Tutorial on RSA Algorithm Theories for Number Theory Noobs
Word2Vec Models Revisited
Posted: August 23, 2019 Updated: August 23, 2019
A Review on the Classic Word2Vec Models
Hierarchical Softmax
Posted: August 17, 2019 Updated: August 17, 2019
Orchestrated Softmax for Fast Language Model Training
Noise Contrastive Estimation
Posted: July 26, 2019 Updated: July 26, 2019
Accelerate the Training of Neural Language Models
Introduction to Variational Inference
Posted: May 25, 2019 Updated: May 25, 2019
Setting Up Foundations to Bayesian Learning
Introduction to Bayesian Filter
Posted: March 21, 2019 Updated: March 21, 2019
Restate Some Basic Concepts and Math in Bayesian Filter
2018
Unveil AlphaZero
Posted: April 2, 2018 Updated: April 2, 2018
A Detailed Interpretation of the AlphaZero Algorithm
2017
Siamese Network on MNIST Dataset
Posted: October 30, 2017 Updated: December 11, 2017
An introduction to Siamese Network and its implementation on MNIST dataset
Google DeepDream in Python
Posted: September 14, 2017 Updated: September 14, 2017
Digital art is soooooo cool! Learning to become an amatuer digital artist.
Getting Started to Build Web Applications on PythonAnywhere
Posted: August 17, 2017 Updated: August 17, 2017
The first step to learn host applications on website.
Making Reinforcement Learning Agent Library
Posted: May 9, 2017 Updated: May 9, 2017
An idea to develop a universal learning agent library; Implementation of Sarsa and Actor-Critic learning algorithm in OpenAI Gym environments.
Monte Carlo Policy Gradient in OpenAI-Gym LunarLander
Posted: May 4, 2017 Updated: May 4, 2017
Implementation of Deep Monte Carlo Policy Gradient learning algorithm in OpenAI Gym environments.
Deep Q-Learning in OpenAI-Gym CartPole
Posted: April 28, 2017 Updated: April 26, 2017
Implementation of Deep Q-Learning algorithm in OpenAI Gym environments.
Deep Q-Learning in Flappy Bird Game
Posted: April 26, 2017 Updated: April 26, 2017
Implementation of Deep Q-Learning algorithm to Play Flappy Bird.