Email: |
xfern@eecs.oregonstate.edu |

Office: |
kelly 3073 |

Office hour: |
MWF 11-12pm, or by appointment |

Class email list: |
cs434-f12@engr.oregonstate.edu |

Machine learning and Data mining is a subfield of artificial intelligence that develops computer programs that can learn from past experience and find useful patterns in data. This field has provided many tools that are widely used and making significant impacts in both industrial and research settings. Some of the application domains include personalized spam filters, HIV vaccine design, handwritten digit recognition, face recognition, credit card fraud detection, unmanned vehicle control, medical diagnosis, intelligent web search, etc.

This
course
will provide a basic introduction to this dynamic and fast
advancing field. Topics include the three basic branches in
this field: (1) Supervised learning for prediction problems
(learn to predict); (2) Unsupervised learning for clustering
data and discovering interesting patterns from data (learn to
understand); and (3) Reinforcement learning for learning to
select actions based on positive and negative feedback (learn
to act). It will have a special focus on the practical side
--- students will not only learn various machine learning and
data mining techniques, but also learn how to apply them to
real problems in practice.

- No
text book required, lecture notes
and reading materials will be posted on the webpage, please
check regularly.
- Useful
References:
*Machine learning*, Tom Mitchell, McGraw-Hill 1997 (Referred to as TM).*Machine learning and pattern recognition*, Chris Bishop, Springer (Referred to as Bishop).

·
Knowledge of basic computer science
principles and skills.

·
Familiarity with the basic
probability theory (Stat314 should be sufficient but not
necessary).

o Slides for
review of basic probability concepts

·
Familiarity with vector calculus
(MTH254 should be sufficient but not necessary) and linear
algebra

o Slides for
review of basic concepts in vector calculus and linear
algebra

Upon
completing
the course, students are expected to:

1)
be able to *apply**supervised
learning algorithms to prediction problems and evaluate
the results.*

2)
be able to *apply
unsupervised learning algorithms to data analysis
problems and evaluate results.*

3)
be able to *apply
reinforcement learning algorithms to control problem and
evaluate results.*

4)
be able to ** take a
description** of a new problem and

**Week
1 (9/24/12-9/28/12) (**

·
Lecture
1
Introduction to basic concepts slides

· Lecture 2 Linear regression slides

· Lecture 3 Linear classifier – perceptron slides

Assignment 1 (Please email the
instructor your answer to the first written question directly.
Use CS434-hw1 in your title of the email.)Data for assignment
1: training; testing . Note that the data is
tab delimited. The first column stores the class labels, which
are either 1, or -1.
Additional data for further testing your perceptron
algorithm.

Solution to assignment 1

·
Lecture 4 Lazy learning: k-nearest
neighbor slides

·
Lecture 5 & 6 Decision tree slides

**Week 3 (10/8/12-10/12/12)**

· Lecture 7 Naive Bayes Classifier slides

·
Assignment 2 Data for assignment 1: training; testing . Note that the data
is comma delimited. The first column stores the class labels,
which are either 1, or 0.

**Week 4 (10/15/12-10/19/12)**

· Lecture 9 Naive Bayes Classifier cont.

· Lecture 10 Logistic regression: slides

· Lecture 11 SVM: slides

**Week 5 (10/23/12-10/27/12)**

· Lecture 12 Unsupervised learning, clustering: Kmeans slides

· Lecture 13 Clustering: HAC slides

· Lecture 14 Clustering: GMM slides

**Week 6 (10/29/12-11/2/12)**

· Lecture 15 Association rules slides

Week 7 (11/5/12-11/9/12)

· Lecture 16: guest lecture. The Impact of Visual Appearance on User Response in Online Display Advertising

· Lecture 17: Dimension reduction: PCA Slides

· Lecture 18: Ensemble learning Slides

**Week 8 (11/12/12-11/16/12)**

· Lecture 19: RL: Markov Decision Processes Slides

· Lecture 20: Markov Decision Processes - value iteration and policy iteration Slides

· Lecture 20: Reinforcement learning: passive learning Slides

**Week 10 (11/26/11-11/31/12)**

· Lecture 21: Reinforcement learning cont. Slides

· Lecture 22: Case study

· Lecture 23: Overview of advanced ML topics