CS 698: Introduction to Machine learning
Fall 2013

Instructor: Usman Roshan
Office: GITC 3802
Ph: 973-596-2872
Office hours: Tue 4-5:30, Wed 2-5
Email: usman@cs.njit.edu

Textbook: Introduction to Machine Learning by Ethem Alpaydin
Grading: 30% mid-term, 30% final exam, 30% course project, 10% assignments
Course Overview: This course is a hands-on introduction to machine learning and contains both theory and application. We will cover classification and regression algorithms in supervised learning such as nave Bayes, nearest neighbor, decision trees, random forests, hidden Markov models, linear regression, logistic regression, and support vector machines. We will also cover dimensionality reduction, unsupervised learning (clustering), feature selection, and kernel methods. We will apply algorithms to solve problems on real data such as digit recognition, text document classification, and prediction of cancer and molecular activity.

Course plan:

Topic	Date	Notes
Introduction, Bayesian learning, and Perl	09/03/2013	Introduction Linear algebra and probability background Bayesian learning Basic Unix command sheet Instructions for AFS login Perl
Bayesian learning and Perl	09/05/2013
Bayesian learning and Perl	09/10/2013	Student project list Perl example 1 Perl example 2 Perl example 3
Bayesian learning and Perl	09/12/2013	Nearest mean algorithm
Nearest means and naive-bayes	09/17/2013	Datasets Naive Bayes algorithm Assignment 1: Implement naive-bayes algorithm
Kernel nearest means	09/19/2013	Balanced error Balanced error in Perl Kernel nearest means
Linear separators	09/24/2013	Hyperplanes as classifiers
Linear separators	09/26/2013	Hardness of separating hyperplanes
Perceptron in Perl	10/01/2013	Assignment 2: Implement perceptron algorithm
Support vector machines	10/03/2013
Support vector machines	10/08/2013	Script to compute average test error
Support vector machines and kernels	10/10/2013	Kernels Multiple kernel learning by Lanckriet et. al. Multiple kernel learning by Gonen and Alpaydin
Cross-validation	10/15/2013	Cross validation svm_learn svm_classify Assignment 3: Implement cross-validation script for SVM run_svm_light.pl
Logistic regression and regularized risk minimization	10/17/2013	Logistic regression Regularized risk minimization Solver for regularized risk minimization linear-bmrm-train linear-bmrm-predict
Review	10/22/2013
Mid-term exam	10/24/2013
Mid-term solution	10/26/2013
Feature selection	10/31/2013	Feature selection NIPS 2003 feature selection contest Contest website Challenge results Challenge results II A comparison of univariate and multivariate gene selection techniques for classification of cancer datasets Feature selection with SVMs and F-score Ranking genomic causal variants with chi-square and SVM
Project proposals	11/05/2013
Project proposals and feature selection	11/07/2013
Dimensionality reduction	11/12/2013	Dimensionality reduction
Dimensionality reduction	11/14/2013	Dimensionality reduction II Maximum margin criterion Laplacian linear discriminant analysis
Dimensionality reduction and unsupervised learning	11/19/2013	Dimensionality reduction III Tutorial on spectral clustering K-means via PCA
Regression	11/21/2013	Clustering
Regression and Hidden Markov models	11/26/2013	Regression Hidden Markov models
Student projects	12/03/2013	Payam, Jie and Turki, and Chris Makson
Student projects	12/05/2013	Johanna, Walter, David and Kia, Nora
Student projects and review for final exam	12/10/2013	Prasad and Fernando, Hechuan, and Indrajit
Final exam	12/19/2013	Room FMH 307 at 2:30pm