MCTS in AlphaGo * MCTS selects actions by lookahead search * see Fig 3 of paper * each edge (s, … More
supervised learning of policy networks (SL) * 13-layer * 30 million positions from KGS Go Server * from 160000 games … More
Original Nature paper: “Mastering the game of Go with deep neural networks and tree search”. Game of GO is the … More
Data representation and processing To represent events in a patient’s timeline, we adopted the FHIR standard (Fast Healthcare Interoperability Resources) … More
Regularization: any modification we make to a learning algorithm to reduce its generalization error but not its training error. Many … More
(The notes for Energy-based Models and Boltzmann Machines are not included here. I will try to add it sometime in … More
Cannot wait to have this in the future!
Neuroscience-Inspired Artificial Intelligence Better understanding biological brains could play a vital role in building intelligent machines More recently, the interaction … More
Reading Note: Realtime Machine Learning the Missing Pieces Context: ML has predominantly focused on training and serving predictions based on … More
This is my reading note for the paper titled “Machine Learning: the hight-interest credit card of technical debt”.
Machine learning is powerful toolkit to build complex systems quickly, but these quick wins does not come for free.
Dilemma: speed of execution and quality of engineering.