45-873 Machine Learning for Business
45-873 Machine Learning for Business
Fall Mini 2, 1998
Prof. Roni Rosenfeld
School of Computer Science, Carnegie Mellon University
This course gives a broad introduction to the techniques of machine
learning, and places those techniques within the context of business
applications. Machine learning is concerned with building computer
programs that learn and improve with experience. The class will start
out with an introduction of the underlying philosophy and methodology
of machine learning, and then move on to hands on application of such
techniques as neural nets and decision trees to real world business
problems.
Time and Place: Tuesdays & Thursdays, 1:30PM--3:20PM, FAST lab, GSIA.
Final Exam: Wednesday, December 16, 1998, 2:00PM--5:00PM,
GSIA Room 145.
Instructor:
Roni Rosenfeld
(roni@cs.cmu.edu), Wean Hall 4109, 412/268-7678. Fax: 412/268-5576.
Office hours: Fridays, 3:30-4:30, or by appointment (set
up via email).
Teaching Assistant:
Rosie Jones
, Cyert Hall 207, 412/268-8492
Office hours: Mondays 12:00-1:00, or by appointment
Course Secretary:
Dorothy Zaborowski (daz+@cs.cmu.edu), Wean Hall 4116. 412/268-3779.
Textbooks:
Machine Learning, by Tom Mitchell, McGraw Hill.
Available at the CMU book store.
Grading:
Will be based on homework (50%) and a final (50%).
Note: you must pass the final to pass the course.
Policy on homework:
- Unless otherwise stated, homework will be assigned on Thursday,
and will be due at the beginning of the next class on Tuesday
, i.e. 5 days after it is assigned. For the next 48 hours, the
homework will be worth 75% credit, unless other arrangements were made
in advance. After that, it will be worth zero credit, unless
other arrangements were made in advance, (but it still needs to
be done). To be considered, a potential hardship should be brought to
the instructor's attention as soon as it becomes known.
- Unless otherwise stated, all homework assignments are to be done
completely on your own, with no communication with anyone except the
TA or the instructor. Communication about the homework continues to
be prohibited until turning them in is worth zero credit (usually
Thursday at the beginning of class).
Announcements: Last updated 10/10/98 (no announcements to date)
Homework Assignments:
Revision Questions
Tentative Syllabus (subject to change)
Lecture 1, Oct 22, 1998:
Introduction; Definition of a Learning Problem (Chapter 1)
( postscript -- 4 MB)
( gzipped postscript -- 300 KB)
( pdf format: adobe acrobat -- 2.5MB)
Lecture 2, Oct 27, 1998:
Introduction to Concept Learning (Chapter 2)
( postscript -- 350 KB)
( postscript 4-to-a-page )
( gzipped postscript -- 100 KB)
( pdf format: adobe acrobat -- 1 MB)
Lecture 3, October 29, 1998:
Concept Learning Continued; Version Spaces
Lecture 4, November 3, 1998:
Decision Trees (Chapter 3)
( postscript -- 530 KB)
( postscript 4-to-a-page )
( gzipped postscript -- 140 KB)
( pdf format: adobe acrobat -- 315 KB )
Lecture 5, November 5, 1998:
Decision Trees (Chapter 3) continued
Lecture 6, November 10, 1998:
Decision Trees continued, overfitting, pruning
Lecture 7, November 12, 1998:
MATLAB Tutorial; combinatorics
Lecture 8, November 17, 1998:
Artificial Neural Networks (Chapter 4)
( postscript) ( pdf format: adobe acrobat)
Lecture 9, November 19, 1998:
Artificial Neural Networks (Chapter 4) continued.
Lecture 10, November 24, 1998:
Evaluating Hypotheses (Chapter 5)
( postscript) ( postscript 4 to a page) ( pdf format: adobe acrobat)
Lecture 11, December 1, 1998:
Bayesian Learning (Chapter 6)
( postscript) ( postscript 4 to a page) ( pdf format: adobe acrobat)
Lecture 12, December 3, 1998:
Bayesian Learning (Chapter 6) continued.
Lecture 13, December 8, 1998:
Guest presentation: Jim Delaney, Mellon Bank.
Instance Based Learning (Chapter 8) ( postscript) ( pdf format: adobe acrobat)
Last modified: Mon Mar 18 13:27:23 EST 2002
http://www.cs.cmu.edu/afs/cs/academic/class/45873-f98/index.html