Stanford Engineering

Machine Learning

This course provides a broad introduction to machine learning and statistical pattern recognition. Topics include: supervised learning (generative/discriminative learning, parametric/non-parametric learning, neural networks, support vector machines); unsupervised learning (clustering, dimensionality reduction, kernel methods); learning theory (bias/variance tradeoffs; VC theory; large margins); reinforcement learning and adaptive control. The course will also discuss recent applications of machine learning, such as to robotic control, data mining, autonomous navigation, bioinformatics, speech recognition, and text and web data processing. (from see.stanford.edu )

Instructor

Professor Andrew Ng,

Computer science

2008

Lecture 01 - An Overview of the Course

Lecture 02 - Linear Regression, Gradient Descent, Normal Equations

Lecture 03 - Locally Weighted Regression, Probabilistic Interpretation, Logistic Regression

Lecture 04 - Newton's Method, Exponential Family, General Linear Models

Lecture 05 - Discriminative Algorithms, Generative Algorithms, Gaussian Discriminant Analysis

Lecture 06 - Neural Network, Applications of Neural Network, Support Vector Machine

Lecture 07 - Optimal Margin Classifier, Karush-Kuhn-Tucker Conditions, SVM Dual

Lecture 08 - Kernels, Mercer's Theorem, Soft Margin SVM, SMO Algorithm, Applications of SVM

Lecture 09 - Bias/variance Tradeoff, Empirical Risk Minimization, The Union Bound, Hoeffding Inequality

Lecture 10 - The Concept of 'Shatter' and VC Dimension, Model Selection, Feature Selection

Lecture 11 - Bayesian Statistics and Regularization, Online Learning, Applications of Machine Learning Algorithms

Lecture 12 - The Concept of Unsupervised Learning

Lecture 13 - Mixture of Gaussian, Mixture of Naive Bayes, Factor Analysis

Lecture 14 - The Factor Analysis Model, 0 EM for Factor Analysis, Principal Component Analysis

Lecture 15 - Latent Semantic Indexing, Independent Component Analysis (ICA), Applications of ICA

Lecture 16 - Applications of Reinforcement Learning, Markov Decision Process (MDP)

Lecture 17 - Generalization to Continuous States, Discretization, Fitted Value Iteration, Optimal Policy

Lecture 18 - Finite Horizon MDPs, The Concept of Dynamical Systems, Linear Quadratic Regulation

Lecture 19 - Debugging Process, Linear Quadratic Regularization, Kalman Filter, Linear Quadratic Gaussian

Lecture 20 - Partially Observable MDPs, Policy Search, Pegasus Algorithm