Machine Learning 2 - Features, Neural Networks | Stanford CS221: AI (Autumn 2019)

For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3GrSkjF Topics: Features and non-linearity, Neural networks, nearest neighbors Percy Liang, Associate Professor & Dorsa Sadigh, Assistant Professor - Stanford University http://onlinehub.stanford.edu/ Associate Professor Percy Liang Associate Professor of Computer Science and Statistics (courtesy) https://profiles.stanford.edu/percy-liang Assistant Professor Dorsa Sadigh Assistant Professor in the Computer Science Department & Electrical Engineering Department https://profiles.stanford.edu/dorsa-sadigh To follow along with the course schedule and syllabus, visit: https://stanford-cs221.github.io/autumn2019/#schedule 0:00 Introduction 0:15 Announcements 1:27 Framework 2:13 Review: optimization problem 2:44 Review: loss functions 6:59 A regression example 14:34 Review: optimization algorithms 18:01 Two components 22:59 Feature vector representations 25:00 Hypothesis class 28:01 Example: beyond linear functions 29:18 Feature extraction + learning 35:13 Linear in what? 38:36 Geometric viewpoint 49:19 Summary so far 50:01 Roadmap 50:46 Motivation 52:48 Decomposing the problem 55:51 Learning strategy 57:11 Gradients 59:34 Neural networks