Semester: | Fall 2018, also offered on Spring 2021 and Fall 2019 |
Time and place: | Tuesday and Thursday, 1.30pm-2.45pm, Mathematical Sciences Building 175 |
Instructor: | Jean Honorio, Lawson Building 2142-J (Please send an e-mail for appointments) |
TAs: |
Hao Ding, e-mail: ding209 at purdue.edu, Office hours: Friday 2pm-4pm, HAAS G50 Ruijiu Mao, e-mail: mao95 at purdue.edu, Office hours: Thursday 11am-1pm, HAAS G50 Md Nasim, e-mail: mnasim at purdue.edu, Office hours: Wednesday 2pm-4pm, HAAS G50 Susheel Suresh, e-mail: suresh43 at purdue.edu, Office hours: Tuesday 3pm-5pm, HAAS G50 |
Date | Topic (Tentative) | Notes |
Tue, Aug 21 |
Lecture 0: linear algebra review Notes: [1] |
Python and Linear algebra in Python |
Thu, Aug 23 |
Lecture 1: perceptron (introduction) Notes: [1] |
|
Tue, Aug 28 |
Lecture 2: perceptron (convergence), support vector machines (introduction) Notes: [1] |
|
Thu, Aug 30 | Lecture 3: nonlinear feature mappings, kernels (introduction), kernel perceptron | Homework 1: due on Sep 4, 11.59pm EST |
Tue, Sep 4 |
Lecture 4: SVM with kernels Notes: [1] |
|
Thu, Sep 6 | (lecture continues) | Homework 2: due on Sep 11, 11.59pm EST |
Tue, Sep 11 |
Lecture 5: anomaly detection (one-class SVM), multi-way classification Notes: [1] |
|
Thu, Sep 13 |
Lecture 6: rating (ordinal regression), PRank, ranking, rank SVM Notes: [1] |
|
Tue, Sep 18 |
Lecture 7: regression, feature selection (information ranking, regularization, subset selection) Notes: [1] |
Homework 3: due on Sep 23, 11.59pm EST |
Thu, Sep 20 |
Lecture 8: ensembles and boosting Notes: [1] |
|
Tue, Sep 25 |
Lecture 9: performance measures, cross-validation, statistical hypothesis testing Notes: [1] |
Homework 4: due on Sep 30, 11.59pm EST |
Thu, Sep 27 | (lecture continues) | |
Tue, Oct 2 | Lecture 10: statistics review, model selection (introduction) | Homework 5: due on Oct 7, 11.59pm EST |
Thu, Oct 4 |
Lecture 11: model selection (VC dimension) Notes: [1] |
|
Tue, Oct 9 | OCTOBER BREAK | |
Thu, Oct 11 | Lecture 12: dimensionality reduction, principal component analysis (PCA) | |
Tue, Oct 16 | MIDTERM (lectures 1 to 11) | 1.30pm-2.45pm, Mathematical Sciences Building 175 |
Thu, Oct 18 | Midterm solution (01, 02, 03) | Homework 6: due on Oct 23, 11.59pm EST |
Tue, Oct 23 | Case Study 1 | |
Thu, Oct 25 | Case Study 2 | |
Tue, Oct 30 | Lecture 13: probability review (joint, marginal and conditional probabilities) |
Project plan due (see Assignments for details) [Word] or [Latex] format |
Thu, Nov 1 | Lecture 14: statistics review (independence, maximum likelihood estimation) | |
Tue, Nov 6 | Lecture 15: generative probabilistic modeling, maximum likelihood estimation, classification | Homework 7: due on Nov 13, at end of lecture |
Thu, Nov 8 | Lecture 16: clustering, mixture models, expectation-maximization (EM) algorithm | |
Tue, Nov 13 | Case Study 3 | Homework 7 solution |
Thu, Nov 15 |
Lecture 17: Bayesian networks (independence) Refs: [1] (not mandatory to be read) |
Preliminary project report, due on Nov 16, 11.59pm EST |
Tue, Nov 20 | Lecture 18: generative probabilistic classification (naive Bayes), non-parametric methods (nearest neighbors) | |
Thu, Nov 22 | THANKSGIVING VACATION | |
Tue, Nov 27 | Lecture 19: non-parametric methods (classification trees) | |
Thu, Nov 29 | FINAL EXAM (lectures 12 to 19, all case studies) |
1.30pm-2.45pm, Mathematical Sciences Building 175 Final project report, due on Dec 1, 11.59pm EST |
Tue, Dec 4 | Final exam solution | |
Thu, Dec 6 | — |