Adrien Lucas EcoffetinTowards Data ScienceAn Intuitive Explanation of Policy Gradient — Part 1: REINFORCEPolicy gradient is behind some of the best RL algorithms out there, yet few people understand the intuition behind its loss function.13 min read·Oct 5, 2018--26--26
Adrien Lucas EcoffetinTowards Data ScienceDeep Learning Book Notes, Chapter 3 (part 1): Introduction to ProbabilityThese are the first part of my notes for chapter 3 of the Deep Learning book. They can also serve as a quick intro to probability. These…18 min read·May 5, 2018--9--9
Adrien Lucas EcoffetinTowards Data SciencePaper repro: Deep Metalearning using “MAML” and “Reptile”How do you learn from very little data? Two recent papers may have the answer. Let’s reproduce them!8 min read·Apr 2, 2018--9--9
Adrien Lucas EcoffetinTowards Data SciencePaper Repro: Deep Neuroevolution“Deep Neuroevolution” showed that simple genetic algorithms can outperform advanced RL algorithms on Atari games. Let’s reproduce it!20 min read·Mar 27, 2018--5--5
Adrien Lucas EcoffetinBecoming Human: Artificial Intelligence MagazineDeep Learning Book Notes, Chapter 2: Linear Algebra for Deep LearningThese are my notes for chapter 2 of the Deep Learning book. They can also serve as a quick intro to linear algebra for deep learning.17 min read·Mar 17, 2018--6--6
Adrien Lucas EcoffetinBecoming Human: Artificial Intelligence MagazinePaper repro: “Self-Normalizing Neural Networks”This post details my experience reproducing “Self-Normalizing Neural Networks” as part of the Nurture.AI NIPS Challenge 2017, as well as my…10 min read·Mar 11, 2018----
Adrien Lucas EcoffetinBecoming Human: Artificial Intelligence MagazineDeep Learning Book Notes, Chapter 1These are my notes on the Deep Learning book. There are many like them but these ones are mine.8 min read·Mar 10, 2018--1--1
Adrien Lucas EcoffetinBecoming Human: Artificial Intelligence MagazineInvestigating Focal and Dice Loss for the Kaggle 2018 Data Science BowlThis post details my experiments and implementations with three important loss functions for the Kaggle 2018 data science bowl, and…7 min read·Mar 6, 2018--2--2
Adrien Lucas EcoffetinBecoming Human: Artificial Intelligence MagazinePaper repro: “Learning to Learn by Gradient Descent by Gradient Descent”This post is the first of what will (hopefully) be a series of deep learning paper reproduction posts.10 min read·Feb 27, 2018--6--6
Adrien Lucas EcoffetinBecoming Human: Artificial Intelligence MagazineBeat Atari with Deep Reinforcement Learning! (Part 2: DQN improvements)Note: Before reading part 2, I recommend you read Beat Atari with Deep Reinforcement Learning! (Part 1: DQN)8 min read·Oct 31, 2017--9--9