CSE190 - A practical introduction to Probability and Statistics

Winter 2007

Course information - Schedule - Additional Resources

(updated January 8, 2006)

Do you want to know how traders in wall street use computers to perform millisecond transactions and make millions of dollars every day? Do you wonder how geneticists are mining genetic sequences for clues on how life works? Would you like to know how gzip works? Are you interested in developing software for computer vision or for speech recognition? If your answer to any of these questions is yes, you are likely to greatly benefit from this course.

Classes will be held in a lecture hall and lab session will be held in a computer lab. Together, the lecture & labs will combine short lectures and hands-on experimentation using Matlab and involving both synthetic and real-world data sets.

The course will cover: Distributions over the real line, density, CDF, mean, variance. Histograms. Independence, expectation, conditional expectation. Distributions over R^n, covariance matrix. Binomial distribution. Poisson Distribution. Chernoff bounds. Entropy. Compression. Maximal likelihood estimation. Bayesian estimation. (Section id: #586079)

Prerequisites: CSE100, CSE101. Non-CSE majors should contact lecturer.

Instructor:

Professor Yoav Freund
email: [my first initial and last name] at ucsd.edu

Office: EBU3b 4126 (CSE Building. 4th Floor)

OH: TBA in my office. Please email me beforehand if you would like to come talk during office hours.

TA:

Deborah Goshorn
email: [my first initial and last name] at ucsd.edu
OH: TBA.

Time and Location:

Lecture: Monday, Wednesday, and Friday from 2:00-3:00 CSB 004
Lab: Monday, Wednesday, and Friday from 3:30-5:30 B210 (computer lab in basement of CSE building)

Prerequisites:

CSE100, CSE101. Non-CSE majors should contact lecturer.

Course Flyer

Topics:
(SUBJECT TO CHANGE FOR WI 07!!)

Distributions over the real line, density, CDF, mean, variance. Histograms.
Independence, expectation, conditional expectation.
Distributions over R^n, covariance matrix. Binomial distribution.
Poisson Distribution.
Chernoff bounds.
Entropy. Compression.
Maximal likelihood estimation.
Bayesian estimation.

Main text

All of Statistics by Larry Wasserman,
Springer, 2004
Available in the UCSD bookstore. Of course, you can find it online as well.

Schedule

Webboard

Use the webboard to ask questions of general interest to the class. Monitor it frequently (daily). The TA and I will post important announcement here and we'll monitor the webboard frequently; you will often get a faster response on the webboard than via email. Of course, do not post anything on the webboard that would violate the course policies on collaboration.

Additional Resources

This page contains links and notes relevant to a particular lecture or topic.

Class structure:

We meet three times a week for lecture and lab. The lecture will teach theoretical concepts and the labs will be applying the concepts via hands-on exploration of the Matlab programming environment. Your attendance at the lectures is critical as it is the primary source of material. (Main text is supplemental to the material we cover in lecture.) During the lab sessions you will be given material that supplements the lecture and you will also be working on lab homework assignments.

Grading:

We will use GradeSource to disseminate grade information. You will receive an email from the TA with your secret number.

Homework (25%): assigned after each lecture (before 3p), and they will typically be due at the start of the next lecture. The goal of the homework is allow you explore the lecture topics in more detail than allowed in class and to prepare you for lecture discussion. Late assignments are not accepted. As there are 20 lectures, there will be roughly be 20 homework assignments. In aggregate, these will require as much work as the homework in other courses. The lowest grade lowest two grades will be dropped when computing the final homework score.
Projects (25%): There will be a handful of smaller projects that tie together concepts throughout the quarter.
Midterm exam(25%) - given during Lecture TBA on TBA.
Final exam (25%) -TBA .

Course Policies:

Submission: Submission details and format vary by assignment. Be sure to read details with each assignment.
Lateness: late submissions will not be accepted. Submit whatever you have by the assignment deadline; late homeworks will not be graded, and will be given a zero. I will only make exceptions for medical or family concerns; get in touch with me as soon as possible if this is the case.
Regrades/Appeals:

You have the right of appeal for grading on all tests; however, an appeal (except for scoring errors) covers the entire test, and may result in an unfavorable judgment on another problem. You have one week from the time the midterms are returned to make appeals, including addition errors on your score. Check it over carefully when you get it.

There is no appeal on homeworks, except for addition errors. No single problem will have a significant impact on your grade.
I will drop the lowest homework score when calculating your grade.

Cooperation: All homeworks, projects, and exams in this course are intended to be done by yourself, and with the help of the textbook, teaching assistants, the instructor. You're allowed to discuss problems with classmates, but only in general terms, and you must specifically avoid discussing any solutions.
Integrity*: Cheating is taken seriously. It is not fair to honest students to take cheating lightly, nor is it fair to the cheater to let him/her go on thinking that is a reasonable alternative in life.

What we do NOT consider cheating: Discussing assignments in groups (with the writeup done separately, later) is not considered cheating.
What we do consider cheating: Discussing assignments with someone who has already completed the problem, or looking at their completed write-up, finding hw solutions on the web or anywhere else. Receiving, providing, or soliciting assistance from another student during a test. Any one homework is not intended to be a grade-maker, but to prepare you for the tests, which are the grade-makers. Cheating on the homeworks is just stupid.
Penalties - anyone copying information or having information copied during a test will receive an F for the class and will not be allowed to drop. They will be reported to their college dean. If you can prove non-cooperative copying took place, your grade may be restored, but you must prove it to the dean -- I don't want to be involved.
Anyone caught cheating on the homework will not be allowed to turn in further homework. Your grade will be based exclusively on the tests and projects (with a suitable penalty applied).

If you have any questions, ask the instructor immediately.

You must also resist the urge to copy material for assignments from the web. Obviously, there are many Statistics courses and there are likely to be similar approaches elsewhere. While I obviously can't forbid you to look at other slides or text material, any evidence of plagiarism from other sources will merit similar consequences.

You would be amazed how easy it is to detect plagiarism these days, so I must reiterative this policy: All homeworks, projects, and exams in this course are intended to be done by yourself.

* Borrowed from Dean Tullsen