Stanford CS221: Artificial Intelligence: Principles and Techniques | Autumn 2019 - Machine Learning 3 - Generalization, K-means | Stanford CS221: AI (Autumn 2019)

For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/30Z6b0p Topics: Generalization, Unsupervised learning, K-means 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 0:34 Review: feature extractor 0:53 Review: prediction score 1:18 Review: loss function 3:42 Roadmap Generalization 3:58 Training error 4:26 A strawman algorithm 5:15 Overfitting pictures 5:51 Evaluation 9:20 Approximation and estimation error 11:27 Effect of hypothesis class size 12:51 Strategy 1: dimensionality 13:34 Controlling the dimensionality 14:21 Strategy: norm 24:21 Controlling the norm: early stopping 27:34 Hyperparameters 30:22 Validation 36:18 Development cycle 55:08 Supervision? 58:12 Word vectors 58:58 Clustering with deep embeddings