Having trouble viewing lectures? Try changing players. Your current player format is html5. Change to flash.

- Class Information
- What Is Machine Learning?
- Applications of Machine Learning
- Key Elements of Machine Learning
- Types of Learning
- Machine Learning in Practice
- What Is Inductive Learning?
- When Should You Use Inductive Learning?
- The Essence of Inductive Learning
- A Framework for Studying Inductive Learning

- Decision Trees
- What Can a Decision Tree Represent?
- Growing a Decision Tree
- Accuracy and Information Gain
- Learning with Non-Boolean Features
- The Parity Problem
- Learning with Many-Valued Attributes
- Learning with Missing Values
- The Overfitting Problem
- Decision Tree Pruning
- Post-Pruning Trees to Rules
- Scaling Up Decision Tree Learning

- Rules vs. Decision Trees
- Learning a Set of Rules
- Estimating Probabilities from Small Samples
- Learning Rules for Multiple Classes
- First-Order Rules
- Learning First-Order Rules Using FOIL
- Induction as Inverted Deduction
- Inverting Propositional Resolution
- Inverting First-Order Resolution

- The K-Nearest Neighbor Algorithm
- Theoretical Guarantees on k-NN
- Distance-Weighted k-NN
- The Curse of Dimensionality
- Feature Selection and Weighting
- Reducing the Computational Cost of k-NN
- Avoiding Overfitting in k-NN
- Locally Weighted Regression
- Radial Basis Function Networks
- Case-Based Reasoning
- Lazy vs. Eager Learning
- Collaborative Filtering

- Bayesian Methods
- Bayes' Theorem and MAP Hypotheses
- Basic Probability Formulas
- MAP Learning
- Learning a Real-Valued Function
- Bayes Optimal Classifier and Gibbs Classifier
- The Naive Bayes Classifier
- Text Classification
- Bayesian Networks
- Inference in Bayesian Networks
- Bayesian Network Review
- Learning Bayesian Networks
- The EM Algorithm
- Example of EM
- Learning Bayesian Network Structure
- The Structural EM Algorithm

- Reverse-Engineering the Brain
- Neural Network Driving a Car
- How Neurons Work
- The Perceptron
- Perceptron Training
- Gradient Descent
- Gradient Descent (Continued)
- Gradient Descent vs. Perceptron Training
- Stochastic Gradient Descent
- Multilayer Perceptrons
- Backpropagation
- Issues in Backpropagation
- Learning Hidden Layer Representations
- Expressiveness of Neural Networks
- Avoiding Overfitting in Neural Networks

- Model Ensembles
- Bagging
- Boosting: The Basics
- Boosting: The Details
- Error-Correcting Output Coding
- Stacking

- Learning Theory
- "No Free Lunch" Theorems
- Practical Consequences of No Free Lunch
- Bias and Variance
- Bias-Variance Decomposition for Squared Loss
- General Bias-Variance Decomposition
- Bias-Variance Decomposition for Zero-One Loss
- Bias and Variance for Other Loss Functions
- PAC Learning
- How Many Examples Are Enough?
- Examples and Definition of PAC Learning
- Agnostic Learning
- VC Dimension
- VC Dimension of Hyperplanes
- Sample Complexity from VC Dimension