Large Scale Machine Learning - UToronto - STA 4273H Winter 2015

Lecture 1 — Machine Learning: Introduction to Machine Learning, Linear Models for Regression Reading: Bishop, Chapter 1: sec. 1.1 - 1.5. and Chapter 3: sec. 1.1 - 1.3. Optional: Bishop, Chapter 2: Backgorund material; Hastie, Tibshirani, Friedman, Chapters 2 and 3. Lecture 2 — Bayesian Framework: Bayesian Linear Regression, Evidence Maximization. Linear Models for Classification. Reading: Bishop, Chapter 3: sec. 3.3 - 3.5. Chapter 4. Optional: Radford Neal s NIPS tutorial on Bayesian Methods for Machine Learning:. Also see Max Welling s notes on Fisher Linear Discriminant Analysis Lecture 3 — Classification Linear Models for Classification, Generative and Discriminative approaches, Laplace Approximation. Reading: Bishop, Chapter 4. Optional: Hastie, Tibshirani, Friedman, Chapter 4. Lecture 4 — Graphical Models: Bayesian Networks, Markov Random Fields Reading: Bishop, Chapter 8. Optional: Hastie, Tibshirani, Friedman, Chapter 17 (Undirected Graphical Models). Mac

讲座 1 —— 机器学习：机器学习导论，线性模型在回归中的应用 阅读材料：Bishop，第 1 章：第 1.1 节至第 1.5 节，以及第 3 章：第 1.1 节至第 1.3 节。选读：Bishop，第 2 章背景资料；Hastie、Tibshirani、Friedman，第 2 章和第 3 章。讲座 2 —— 贝叶斯框架：贝叶斯线性回归，证据最大化。线性模型在分类中的应用。阅读材料：Bishop，第 3 章：第 3.3 节至第 3.5 节，第 4 章。选读：Radford Neal 在 NIPS 上的贝叶斯机器学习方法教程。亦请参阅 Max Welling 关于费舍尔线性判别分析的笔记。讲座 3 —— 分类：分类的线性模型，生成式和判别式方法，拉普拉斯近似。阅读材料：Bishop，第 4 章。选读：Hastie、Tibshirani、Friedman，第 4 章。讲座 4 —— 图模型：贝叶斯网络，马尔可夫随机场。阅读材料：Bishop，第 8 章。选读：Hastie、Tibshirani、Friedman，第 17 章（无向图模型）。