Table of Contents

To Study List

Network

• Wavenet: A Generative Model for Raw Audio : arxiv, pdf, page
• Parallel Wavenet: Fast High-Fidelity Speech Synthesis : pdf, page
• Neural Discrete Representation Learning(VQ-VAE) : arxiv, pdf, slide, page
• Dynamic Routing Between Capsules : arxiv, pdf
• XGAN: Unsupervised Image-to-Image Translation for many-to-many Mappings : arxiv, pdf

Courses

• CS231n : page, github
• CS224s : page

Dataset

• Fashion-MNIST : github, benchmark
• Kaggle-Speech : page