550.436 - Data Mining

550.436
DATA MINING
FALL 2007

Instructor:
Bruno Jedynak, 208-B Whitehead Hall, (bruno.jedynak "splat" jhu.edu )

Office Hours:
Th 3:15-4:15pm or by appointment.

Teaching Assistant:
Elizabeth Reilly, 202-A Whitehead Hall, (reilly "splat" ams.jhu.edu)

Office Hours:
MW 5pm-6pm

Lectures:
MTW 3-3:50pm, Hodson 311.

Section:
F 12-12:50pm, Shaffer 1.

Textbook:
Introduction to Data Mining by Pang-Ning Tan, Michael Steinbach, and Vipin Kumar

Description:
This course will cover advanced topics and methods in exploratory data analysis and modeling, often lumped under the heading Data Mining, or other terms such as Machine Learning or Knowledge Discovery. Topics will include model building methods, data quality analysis and methods, neural networks, decision trees, principal components, support vector machines, clustering techniques, association rules, and other machine learning and statistical techniques. The focus will be on application of methods to real data and doing data mining on the computer. Some parts to the course will involve heavier mathematics and theory.

ANNOUNCEMENTS:

Office Hours change for the week of September 24: I will be holding office hours on Monday, September 24 from 5-7pm and none on Wednesday, September 26. My office hours will return to normal the week of October 1.
Late homework will NOT be accepted. If you anticipate being unable to hand your homework in on time for a good reason, please speak with ME before the due date.
For the official course website, please logon to WebCT. If you do not have access to this course, then email Bruno Jedynak with your name and course number.

Material used in section:

September 21: PCA in WEKA
October 5: Jörg Tiedemann's example of how to interpret J48 classifier output.
October 26: Introduction to Neural Networks
November 16: Letter Recognition, Web Robots, and SVM

Instructor:	Bruno Jedynak, 208-B Whitehead Hall, (`bruno.jedynak "splat" jhu.edu` )
Office Hours:	Th 3:15-4:15pm or by appointment.
Teaching Assistant:	Elizabeth Reilly, 202-A Whitehead Hall, (`reilly "splat" ams.jhu.edu`)
Office Hours:	MW 5pm-6pm
Lectures:	MTW 3-3:50pm, Hodson 311.
Section:	F 12-12:50pm, Shaffer 1.
Textbook:	Introduction to Data Mining by Pang-Ning Tan, Michael Steinbach, and Vipin Kumar
Description:	This course will cover advanced topics and methods in exploratory data analysis and modeling, often lumped under the heading Data Mining, or other terms such as Machine Learning or Knowledge Discovery. Topics will include model building methods, data quality analysis and methods, neural networks, decision trees, principal components, support vector machines, clustering techniques, association rules, and other machine learning and statistical techniques. The focus will be on application of methods to real data and doing data mining on the computer. Some parts to the course will involve heavier mathematics and theory.
ANNOUNCEMENTS:	Office Hours change for the week of September 24: I will be holding office hours on Monday, September 24 from 5-7pm and none on Wednesday, September 26. My office hours will return to normal the week of October 1. Late homework will NOT be accepted. If you anticipate being unable to hand your homework in on time for a good reason, please speak with ME before the due date. For the official course website, please logon to WebCT. If you do not have access to this course, then email Bruno Jedynak with your name and course number.