Welcome to Depth First Learning!
DFL is a compendium of curricula to help you deeply understand Machine Learning.
Each of our posts are a self-contained lesson plan targeting a significant research paper and complete with readings, questions, and answers.
We can guarantee that honestly engaging the material will leave you with a thorough understanding of the methods, background, and significance of that paper.
In this curriculum, you will explore Game Theory and Counterfactual Regret Minimization in order to understand techniques for solving two person zero-sum games of incomplete information. ⟹
In this curriculum, you will learn about two-person zero-sum perfect information games and develop understanding to completely grok AlphaGoZero. ⟹
Trust Region Policy Optimization
TRPO is a model-free algorithm for optimizing policies in reinforcement learning by gradient descent. It represents a significant improvement over previous methods in its scalability and consequently has enjoyed widespread success. ⟹
InfoGAN is an extension of GANs that learns to represent unlabeled data as codes. Representation learning is an important aspect of unsupervised learning, and GANs are a flexible and powerful interpretation. This makes InfoGAN an important and interesting stepping stone in representation learning. ⟹
What Is This
Welcome to Depth First Learning. ⟹