Style-based Recalibration Module (SRM) Channel Attention
In this post, we will cover a novel form of channel attention called the Style Recalibration Module (SRM), an extension of the popular TPAMI paper: Squeeze-and-Excitation Networks.
The Machine Learning Practitioner's Guide to Reinforcement Learning: Overview of the RL Universe
In this post, we describe the anatomy of how most Deep Reinforcement Learning algorithms work. We also cover the motivation to use RL over standard machine learning, On-Policy v/s Off-Policy learning, the Exploration-Exploitation Tradeoff, and many more important RL concepts.