Semester: | Fall 2020, also offered on Spring 2020, Spring 2018, Fall 2017 and Fall 2016 |
Time and place: | Tuesday and Thursday, 3.00pm-4.15pm EST |
Instructor: | Jean Honorio (Please send an e-mail for appointments) |
TAs: |
Chuyang Ke, e-mail: cke at purdue.edu, Office hours: Monday 10am-noon EST Kevin Bello, e-mail: kbellome at purdue.edu, Office hours: Friday 2pm-4pm EST |
Date | Topic (Tentative) | Notes |
Tue, Aug 25 | Lecture 1: perceptron (introduction) | Homework 0: due on Aug 27, 11.59pm EST - NO EXTENSION DAYS ALLOWED |
Thu, Aug 27 | Lecture 2: perceptron (convergence), max-margin classifiers, support vector machines (introduction) | Homework 0 due - NO EXTENSION DAYS ALLOWED |
Tue, Sep 1 | Lecture 3: nonlinear feature mappings, kernels (introduction), kernel perceptron | Homework 0 solution |
Thu, Sep 3 |
Lecture 4: SVM with kernels, dual solution Refs: [1] [2] (not mandatory to be read) |
Homework 1: due on Sep 10, 11.59pm EST |
Tue, Sep 8 |
Lecture 5: one-class problems (anomaly detection), one-class SVM, multi-way classification, direct multi-class SVM Refs: [1] [2] [3] [4] (not mandatory to be read) |
|
Thu, Sep 10 |
Lecture 6: rating (ordinal regression), PRank, ranking, rank SVM Refs: [1] [2] (not mandatory to be read) |
Homework 1 due |
Tue, Sep 15 | Lecture 7: linear and kernel regression, feature selection (information ranking, regularization, subset selection) | Homework 2: due on Sep 22, 11.59pm EST |
Thu, Sep 17 | Lecture 8: ensembles and boosting | |
Tue, Sep 22 | Lecture 9: performance measures, cross-validation, bias-variance tradeoff, statistical hypothesis testing | Homework 2 due |
Thu, Sep 24 | Lecture 10: model selection (VC dimension, generalization, structural risk minimization) | Homework 3: due on Oct 1, 11.59pm EST |
Tue, Sep 29 | Lecture 11: probability review (joint, marginal and conditional probability), independence, maximum likelihood estimation | |
Thu, Oct 1 | Lecture 12: generative probabilistic modeling, maximum likelihood estimation, decision boundary | Homework 3 due |
Tue, Oct 6 | Lecture 13: mixture models, EM algorithm, convergence, model selection | |
Thu, Oct 8 | MIDTERM (lectures 1 to 12) |
Start: Thursday October 8, 3.00pm EST End: Friday October 9, 3.00pm EST |
Tue, Oct 13 | (midterm solution) | |
Thu, Oct 15 | — |
Project plan due (see Assignments for details) [Word] or [Latex] format |
Tue, Oct 20 |
Lecture 14: active learning, kernel regression, Gaussian processes Refs: [1] (not mandatory to be read) |
|
Thu, Oct 22 | Lecture 15: dimensionality reduction, principal component analysis (PCA), kernel PCA | Homework 4: due on Oct 29, 11.59pm EST |
Tue, Oct 27 |
Lecture 16: collaborative filtering (matrix factorization), structured prediction (max-margin approach) Refs: [1] (not mandatory to be read) |
|
Thu, Oct 29 |
Lecture 17: Bayesian networks (motivation, examples, graph, independence) Refs: [1] [2] (not mandatory to be read) |
Homework 4 due |
Tue, Nov 3 |
Lecture 18: Bayesian networks (independence, equivalence, learning) Refs: [1] [2] [3, chapters 16-20] (not mandatory to be read) |
|
Thu, Nov 5 |
Lecture 19: Bayesian networks (introduction to inference), Markov random fields, factor graphs Refs: [1] [2] (not mandatory to be read) |
Preliminary project report due (see Assignments for details) - NO EXTENSION DAYS ALLOWED |
Tue, Nov 10 | — | |
Thu, Nov 12 |
Lecture 20: Markov random fields (inference, learning) Refs: [1] [2] [3, chapters 16-20] (not mandatory to be read) |
|
Tue, Nov 17 | (lecture 20 continues) | |
Thu, Nov 19 | Lecture 21: Markov random fields (inference in general graphs, junction trees) | Final project report due (see Assignments for details) - NO EXTENSION DAYS ALLOWED |
Mon, Nov 23 | FINAL EXAM (lectures 13 to 21) |
Start: Monday November 23, 4.15pm EST End: Tuesday November 24, 4.15pm EST |
Thu, Nov 26 | THANKSGIVING VACATION | |
Tue, Dec 1 | (final exam solution) |