Matthew ChanFollow-ups: Cart-Pole Balancing with Q-NetworkIn my previous post on Cart-Pole Balancing with Q-Learning, I discretized the state-space into multiple buckets to construct a Q-table…Nov 15, 20167Nov 15, 20167
Matthew ChanCart-Pole Balancing with Q-LearningThe OpenAI Gym provides many standard environments for people to test their reinforcement algorithms. These environments include classic…Nov 13, 201617Nov 13, 201617
Matthew ChanBuilding a Deep Handwritten Digits Classifier using Microsoft Cognitive ToolkitThe MNIST handwritten digits classification problem has long been used as the “Hello World” of machine learning. The recently updated…Nov 7, 2016Nov 7, 2016
Matthew ChanA Saturday at the Amazon Alexa HackathonPreviously, I have gone to a short 2-hour workshop ran by someone from the Amazon Alexa team. For most of that workshop, the presenter…Sep 29, 2016Sep 29, 2016