Fill More Holes in Deep Learning

Harness TensorFlow Dataset API for Real Applications

Traditional Computer Vision Techniques Boosted Deep Learning

Mathematical Proof of the Maximum Likelihood Estimation of N-Gram Model Parameters

Using Jupyter Notebook on Docker

Visualization of TensorBoard on Docker

Never Jump Out of Log Domain

Some Jekyll Notes

Fill Up Some Probability Holes

Understand Prefix-Free Code, Huffman Coding, and Try it Using Library Tools

Understand How Pseudolikelihood Works in Graphical Models

Ever Think of Backpropagation Through Max-Pooling Layer?