CSI5387
Concept Learning Systems/Machine Learning
Instructor
Nathalie Japkowicz
Office: STE 5-029
Phone: 562-5800 ext. 6693
E-mail: nat@site.uottawa.ca
Meeting Times and Locations
Office Hours and Locations
Overview
Machine Learning is the area of Artificial Intelligence concerned with
the problem of building computer programs that automatically improve with
experience. The intent of this course is to present a broad introduction to the
principles and paradigms underlying machine learning, including presentations
of its main approaches, discussions of its major theoretical issues, and
overviews of its most important research themes.
Course Format
The course will consist of a mixture of regular lectures and student
presentations. The regular lectures will cover descriptions and discussions of
the major approaches to Machine Learning as well as of its major theoretical
issues. The student presentations will focus on the most important themes we
survey. This year, the focus will be on Big Data Analysis.
Evaluation
Students will be evaluated on short written commentaries and oral
presentations of research papers (15%), on two homework assignments (25%), on a
final exam (20%), and on a final class project of the student's choice (40%).
For the class project, students can propose their own topic or choose from a
list of suggested topics which will be made available at the beginning of the
term. Project proposals will be due in mid-semester. For the research paper
commentaries, students will work in teams of 3 or 4. However, homework,
presentations and projects must be submitted/done individually.
Pre-Requisites
Students should have reasonable exposure to Artificial Intelligence and
some programming experience in a high level language.
Required Textbooks
Additional References .
Class Notes
Class
notes are available here.
Other Reading Material
Articles for the students to
critique and present will be provided in a zipped directory by e-mail, or as
they become available.
List of Major Approaches
Surveyed
List of Theoretical Issues
Considered
List of Major Themes
Surveyed
All
the themes surveyed in this course pertain to the currently very popular
extension of machine learning known as “Big Data Analysis”. The themes surveyed
will be long to the following list:
·
Graph
Mining
·
Mining
Social Networks
·
Data
Streams Mining
·
Unstructured
or Semi-Structured Data Mining
·
Data
Mining with Heterogeneous Sources
·
Spatio-Temporal
Data Mining
·
Issues
of Trust and Provenance in Data Mining
·
Privacy
in Data Mining
Homework Related material:
·
List of Themes/Papers for
this year: The papers read by
the class this year will be distributed by e-mail or on Blackboard. The theme
for this year is Big Data Analysis. Each team of 3 or 4 students must submit
their summary and critique every week that a chapter is read.
·
Presentations: Presentations will be done individually. Each
student will speak for approximately 15 minutes and answer some of the
students/instructor’s questions. The schedule for presentations is available
here.
·
Assignment 1: Supervised Learning Part I, Unsupervised
Learning, Evaluation Techniques Part I. Handed out on Monday of Week 5; to
return on the Wednesday of Week 8.
·
Assignment 2: Supervised Learning Part II, Evaluation
Techniques Part II, Association Mining. Handed out on the Wednesday of Week 8;
to return on the Wednesday of Week 11
·
Final Exam: The final exam will take place in class, on
the Monday of Week 14. (Last day of classes)
Course Support:
· Suggested
Outline for Paper Commentaries
· Guidelines
for the Final Project Report
Machine Learning Ressources
on the Web:
· David
Aha's Machine Learning Resource Page
· WEKA
· Free Book: Information
Theory, Inference, and Learning Algorithms, David MacKay
· R
Code from the Japkowicz and Shah Evaluation Book
Syllabus:
Week |
Topics |
Readings |
Week 1: Jan 12 |
Organizational
Meeting,
Theoretical and Practical Overview of Machine Learning, Philosophical roots of machine
Learning |
Texts: ·
Flach: Prologue, Chapters 1, 2 ·
Japkowicz & Shah : Chapter 1 ·
Class Notes : Week 1 ·
|
Week 2: Jan 19 |
Versions Space Learning, Decision Tree Learning |
Texts: ·
Flach: Chapters 4, 5 ·
Japkowicz & Shah: Chapter 2 ·
Class Notes: Week 2 – Part I & Part II |
Week 3: Jan 26 |
Artificial
Neural Networks, Bayesian Learning |
Texts: ·
Flach: Sections 7.1-2, Chapter 9 ·
Class Notes: Week 3 – Part I & Part II |
Week 4: February
2 |
Texts: ·
Japkowicz & Shah: Chapters 3-6 ·
Flach: Chapter 12 ·
Class Notes: Week 4 |
|
Week 5 February 9 |
·
Instance-Based Learning and unsupervised learning ·
Weekly Theme: Introduction to Big Data
Analysis Homework
1: Handed
out on Monday; Due: Wednesday, Week 8 |
Texts: ·
Flach: Chapter 8 ·
Class Notes: Week 5 – Part I & Part II ·
Weekly Theme papers |
Week 6: Feb 16 |
STUDY BREAK |
STUDY BREAK |
Week 7 Feb 23 |
·
Rule Learning/Association
Mining, ·
Weekly Theme: Data Stream Mining Project Proposal DUE on Wednesday |
Texts: ·
Flach: Chapter 6 ·
Class Notes: Week 7 ·
Weekly Theme papers |
Week 8: March 2 |
·
Support Vector Machines, ·
Weekly Theme: Mining Social Networks Homework 1 DUE on Wednesday Homework 2: Handed out on Wednesday; Due:
Wednesday, Week 11 |
Texts: ·
Flach: Chapter 7 ·
Class Notes: Week 8 ·
Weekly Theme papers |
Week 9: March 9 |
·
Classifier Ensembles, ·
Weekly Theme: Trust, Provenance and Privacy |
Texts: ·
Flach: Chapter 11 ·
Class Notes: Week 9 ·
Weekly Theme papers |
Week 10: March
16 |
·
Features ·
Weekly Theme: Applications of Big Data Analysis
I: Science, Medicine and Cyber Security |
Texts: ·
Flach: Chapter 10 ·
Class Notes: Week 10 ·
Weekly Theme papers |
Week 11: March
23 |
·
Genetic Algorithms, ·
Weekly Theme: Applications of Big Data Analysis II: Industry and Business Homework 2: DUE on Wednesday |
Texts: ·
Class Notes: Week 11 ·
Weekly Theme papers |
Week 12: March
30 |
MONDAY, WEDNESDAY: FINAL PROJECT PRESENTATIONS |
|
Week 13: April 6 |
Wednesday: Review for the FINAL EXAM |
|
Week 14: April
13 |
MONDAY: FINAL EXAM -- LAST DAY OF CLASSES |
|