# Replace derivatives in back propagation

When I tried to calculate the derivative of ReLU, i.e. $Y = max(0, X)$ where Y, X are (N, H) dimension matrix, I was astounded. Isn’t it a 4-dimension array of shape (N, H, N, H)? Read more

# Statitical Learning Theory Note by Hisashi Kashima

The course was taught in Spring 2017. The course material is here. Read more

# Using both Python 2 and 3

I recently switch to Anaconda for convenient environment for studying machine learning, as suggested by CS231n. Then I encounter the problem of switching back and forth between Python 2 and 3, again. Fortunately, Anaconda provide a handy solution for this problem. Then I go to this SO post and it works magically. Conda Both of the posts su... Read more

# Easy JS Unit Test with Jasmine and Karma

Jasmine is the testing framework. Karma is the test runner. Working with them when writing unit tests is… cool. Read more

# Create CLI for my blog

If you are kind enough to check my code for hosting this blog, you can see that I am using some Ruby scripts to create post templates, or rename post. Read more