10701 Machine Learning

Consult this page for course description, policies and links to previous course pages and exams.

Course Description

Machine learning seeks to address the problems and challenges surrounding the theory and practice of machines that improve their performance with respect to a measurable goal with experience. Some examples include automated speech recognition systems, medical decision aids which suggest courses of action to a doctor based on clinical test results, personalized information retrieval engines which learn from a particular user's previous queries and choice of answers and robots which learn to navigate in their environment by exploration.

The aim of the course is to give PhD students a thorough training in the current theory, models and algorithms required to perform research in machine learning. Being such a multidisciplinary field, the course spans materials from classical and bayesian statistics, information theory, machine learning, and data mining.

Students with an existing knowledge of probability, statistics and algorithms will be at an advantage, but the class is designed so that anyone with a strong mathematical background can quickly catch up.

If you are interested in machine learning, but are not a PhD student, we suggest the master's level course on Machine Learning, 10-601.

Textbook

Textbook: Pattern Recognition and Machine Learning, Chris Bishop
Optional textbook: Machine Learning, Tom Mitchell.
Additional readings will be made available as appropriate.

Grading

The requirements of this course consist of participating in lectures, midterm and final exams, 5 problem sets and a project. This is a PhD level class, and the most important thing for us is that by the end of this class students understand the basic methodologies in machine learning, and be able to use them to solve real problems of modest complexity. The grading breakdown is the following:

Homework (25%, 5 assignments, 5% each)
Midterm (20%)
Final exam (30%)
Final project (20%)
Class participation (5%)

Exams

The midterm and final exams will be open book and open notes. Computers will not be allowed.
Midterm exam date: 3/5
Final exam date: 5/5
Project presentation: 4/28
Rescheduling of exams: It is impossible for us to accommodate individual requests to reschedule the exams. It is your responsibility to assure that you are in town and available for the final exam.

Homework resources and collaboration policy

Homeworks and exams may contain material that has been covered by papers and webpages. Since this is a graduate class, we expect students to want to learn and not google for answers.

Homeworks will be done individually: each student must hand in their own answers. It is acceptable for students to collaborate in figuring out answers and helping each other solve the problems. We will be assuming that, as participants in a graduate course, you will be taking the responsibility to make sure you personally understand the solution to any work arising from such collaboration. You also must indicate on each homework with whom you collaborated.

The final project should be carried out by teams of 2-3 students. Students in this class come from many different departments and schools within CMU. We highly encourage students to form interdisciplinary groups involving students from multiple departments.

Note to people outside CMU

Please feel free to reuse any of these course materials that you find of use in your own courses. We ask that you retain any copyright notices, and include written notice indicating the source of any materials you use.

Late homework policy

Grading policy for late homework:

Homework is worth full credit at the beginning of class on the due date.
It is worth 75% for the next 24 hours.
It is worth half credit from 24 to 96 hours after the due date (homeworks are usually due on Thursday so this means that if you hand them in by the following Monday you will can receive 50% of the total grade).
It is worth zero credit after that.

You must turn in at least 4 of the 5 homeworks, even if for zero credit, in order to pass the course.
Turn in all late homework assignments to Michelle Martin.

Homework regrades policy

If you feel that we have made an error in grading your homework, please turn in your homework with a written explanation to Michelle Martin and we will consider your request. Please note that regrading of a homework may cause your grade to go up or down.

Previous Course Homepages

Here are a bunch of course homepages from earlier years, where you can find slides, examples of homeworks, etc.

Previous Exams

Here are some example questions here for studying for the midterm/final. Note that these are exams from earlier years, and contain some topics that will not appear in this year's exams. And some topics will appear this year that do not appear in the following examples.

Additional midterm examples (questions, solutions)
The 2001 midterm (midterm, solutions)
The 2002 midterm (midterm, solutions)
The 2003 midterm (midterm, solutions)
The 2004 midterm (midterm, solutions)
The 2005 spring midterm (solutions)
The 2005 fall midterm (solutions)
The 2006 fall midterm (midterm, solutions)
The 2007 spring midterm (midterm, solutions)
The 2008 spring midterm (solutions)
The 2008 fall midterm (solutions)
The 2001 final (final, solutions)
The 2002 final (final with some figs missing, solutions)
The 2003 final (final, solutions)
The 2004 final (solutions)
The 2006 fall final (final, solutions)
The 2007 spring final (final, solutions)
The 2008 fall final (final, solutions)

[validate xhtml]