What does the gradient flowing through batch normalization looks like ?

This past week, I have been working on the assignments from the Stanford CS class CS231n: Convolutional Neural Networks for Visual Recognition. In particular, I spent a few hours deriving a correct expression to backpropagate the batchnorm regularization (Assigment 2 - Batch Normalization) . While this post is mainly for me not to forget about what insights I have gained in solving this problem, I hope it could be useful to others that are struggling with back propagation.

Read More

AGU fall meeting: Part 3 - Abstract similarities

American Geophysical Union (AGU) meeting is a geoscience conference hold each year around Christmas in San Francisco. It represents a great opportunity for PhD students like me to show off their work and enjoy what the west coast has to offer. However, with nearly 24 000 attendees, AGU Fall Meeting is also the largest Earth and space science meeting in the world. As such, it represents an interesting data set to dive into the geoscience academic world.

Read More

AGU fall meeting - Part 2 : Exploratory analysis

American Geophysical Union (AGU) meeting is a geoscience conference hold each year around Christmas in San Francisco. It represents a great opportunity for PhD students like me to show off their work and enjoy what the west coast has to offer.

Read More

AGU fall meeting - Part1 : Scrapping the data

American Geophysical Union (AGU) meeting is a geoscience conference hold each year around Christmas in San Francisco. It represents a great opportunity for PhD students like me to show off their work and enjoy what the west coast has to offer.

Read More