Orchestrated Softmax for Fast Language Model Training

Regularization for Classification Models

Some Theories for Machine Learning Optimization

Accelerate the Training of Neural Language Models

The Math of Dropout You Know and Don't Know

Setting Up Foundations to Bayesian Learning

Restate Some Basic Concepts and Math in Bayesian Filter

CycleGAN-Based Voice Conversions

CycleGAN-Based Image-to-Image Translations

A Brief Review on Stephen Masland's Machine Learning Textbook

Understand Why We Initialize the Weights in This Way