tech
-
Back-to-Basics Weekend Reading - Dropout: A Simple Way to Prevent Neural Networks from Overfittin
I noticed that I have never read the original dropout paper even though it’s very common and I’ve known it for a long time.
-
Creating a custom environment in OpenAI Gym - Blocking Maze
This short post introduces how to create your own OpenAI gym environment.
-
Quick recap of basic exploration strategy in RL - epsilon-greedy
Back to basics. I found that I didn’t write anything about reinforcement learning (RL) since I started blogging, although my research area has been RL for a while. I’m loving GANs too much these days :)
-
Conditional GANs (cGANs) and its variations
Back to basics. As a series of my “reinventing-the-wheels” project to understand things well, I took some time to reimplement Conditional Generative Adversarial Nets from scratch. This is a note on it.
-
Fighting to mode collapse 1 - Feature Matching
In this post, I’ll implement feature matching, a simple tehnique to mitigate GANs mode collapse.