COSC-575: Machine Learning

Spring 2012

Class Time:	MW 5:00–6:15 PM
Classroom:	WGR 206

Instructor:	Mark Maloof
Office:	325 St. Mary's
Mailbox:	St. Mary's
Office Hours:	In-person (325 STM): TR 11:00 AM–12:00 PM; online: M 10:30–11:30 AM and W 3:00–4:00 PM; or by appointment. Send me an email to get the Zoom link for online office hours. (or by appointment)

Course Description

This graduate lecture surveys the major research areas of machine learning. Through traditional lectures, programming projects, paper presentations, and research projects, students learn (1) to understand the foundations of machine learning, (2) to comprehend, analyze, and critique papers from the primary literature, (3) to replicate studies described in the primary literature, and (4) to design, conduct, and present their own studies. The course compares and contrasts machine learning with related endeavors, such as statistical learning, pattern classification, data mining, and information retrieval. Topics include Bayesian decision theory, instance-based approaches, Bayesian methods, decision trees, rule induction, density estimation, linear classifiers, neural networks, support vector machines, ensemble methods, learning theory, evaluation, and applications. Time permitting additional topics include genetic algorithms, unsupervised learning, semi-supervised learning, outlier detection, sequence learning, and reinforcement learning.

Primary Text:

Machine Learning, by Mitchell

Schedule

Introduction: Definitions, Areas, History, Paradigms
Bayesian Decision Theory
Instance-based learning: k-NN, kd-trees
Bayesian learning: Bayes' Theorem, naive Bayes
Evaluation: Train/Test Methodologies
Density estimation: Parametric, Non-parametric, Bayesian
Decision Trees: ID3, C4.5
Decision Trees: Stumps, VFDT; Midterm Exam
Rule Learning: Ripper, OneR
Ensemble Methods: Bagging, Boosting
Ensemble Methods: Random Forests, Voting, Weighting
Neural Networks: Linear classifiers, Perceptron
Neural Networks: Multilayer networks, Back-propagation
Support Vector Machines: Perceptron, Dual representation
Support Vector Machines: Margins, Kernels, Training, SMO
Outlier Detection: Parametric, Non-parametric, Density-based

Course Policies

Assignments and Grading

Programming Projects, 40%
- Project 1, assigned W 1/11, due W 2/1, 10 points
- Project 2, assigned W 2/1, due R 3/1, 10 points
- Project 3, assigned W 2/22, due R 3/22, 10 points
- Project 4, assigned W 3/21, due R 4/12, 10 points
Midterm Exam, W 3/14, 15%
Final Exam, 5/9, 4–6 PM, 15%
Paper Presentations, 10%
Research Project, 20%
- Prospectus, due 3/11 at 10 PM
- Presentation, 4/23, 5 points
- Paper, due 4/30 @ 11:59 PM, 15 points

Grading

String Grades::getLetterGrade()
{
  if (grade >= 94)
    return "A";
  else if (grade >= 90)
    return "A-";
  else if (grade >= 87)
    return "B+";
  else if (grade >= 84)
    return "B";
  else if (grade >= 80)
    return "B-";
  else if (grade >= 67)
    return "C";
  else
    return "F";
} // Grades::getLetterGrade

Resources