Date |
|
Lecture |
Reading Materials |
Week 1 |
I2ml- chapter 1 |
||
Week 2 |
Hypothesis spaces, VC-dim, Regression, variance-bias trade off, training and validation, error metrics. |
I2ml chapter 2 ML 7.4.2, 7.4.3 |
|
2/5/07 |
Week 3 |
Bayesian Decision Theory, Bayesian Networks.
|
I2ml chapter 3 |
Week 4 |
Bayesian Decision theory,
parametric methods: Parameter Estimation, MLE, Bayes Estimator, Bias and Variance,
Parametric Classification, Multivariate Data |
I2ml - 4.1->4.5, 5.1 -> 5.7 |
|
Week 5 |
Guest Lecture: Prof. Michael Littman- Reinforcement Learning |
I2ml chapter 16 |
|
Week 6 |
parametric methods: Cont. Multivariate Data |
I2ml chapter 5 I2ml - chapter 10 ML - chaptter 3
|
|
Week 7 |
Artificial Neural Networks: Perceptron,
Perceptron learning rule, delta rule Artificial Neural Networks
Multilayered Perceptron, Backpropagation, Structured NN, and Dimensionality
Reduction using NN. |
I2ml chapter 11 |
|
Week 8 |
Mid Term |
|
|
Week 9 |
Density Estimation and Clustering Density Estimation: Nonparametric density estimation, Instant based learning, nonparametric regression. Unsupervised Learning Clustering: K-means, hierarchical
clustering, mean shift, graph spectral clustering |
ML 8.1, 8.2, 8.5, I2ML chapters 7 and 8
|
|
4/2/07 |
Week 10 |
Guest Lecture: Prof. Vladimir Pavlovic : Graphical Models and Sequence Learning |
|
Week 11 |
Linear Discrimination:
Generalized linear models and kernel functions, kernel trick. Linear Discrimination:
Support Vector Machines |
I2ml chapter 10 |
|
Week 12 |
Nonlinear dimensionality Reduction: Manifold Learning, Local Linear Embedding (LLE), Isomap. |
I2ml Chapter 6 |
|
Week 13 |
|
||
Week 14 |
I2ml Chapter 13 |
||
Combining multiple learners: Voting, Bagging, Boosting, AdaBoost, Mixture of Experts. |
I2ml Chapter 15 |
||
|
|
|
|