This course is taught by
Margaret Fleck
mfleck@illinois.edu
3214 Siebel or 1222 Siebel (inside the CS Undergraduate Office)
Neither office has a working phone, so please use email to contact me or post on our piazza forum
This course provides an introductory survey of concepts and techniques in artificial intelligence. We will cover methods for search, classification, reasoning, and machine learning. We will also look at applications including core AI (games, planning), robotics, computer vision, and natural language understanding.
This course assumes that you have taken data structures (CS 225) and probability and statistics (CS 361, ECE 313, STAT 400, MATH 461, or BIOE 310). Notice that our data structures course implies that you have taken discrete math (CS 173) and Calculus I. CS 440 is intended to be a first course in AI. If you have already taken a specialized AI course (e.g. CS 446), be prepared for a repeat of some familiar material.
Our meeting time is MWF 9-9:50 in 0027/1025 Campus Instruction Facility (aka the big auditorium).. There will be in-class quizzes every other Friday starting with week 3. The makeup for each quiz will be in class the following Friday. To accommodate the quizzes and makeups, some lecture material may be pre-recorded. In-class lectures will be recorded and lecture notes posted.
MPs will be due alternate Fridays starting in week 4.
An office hour schedule (instructor and TAs) will be posted during the first week of classes. Meanwhile, catch Margaret at the end of lecture to talk or set up a time to talk. Office hours will be a mix of in-person and online, depending on the current state of diseases on campus (e.g. Covid 19) and how crowded our building is.
The textbook is Russell and Norvig, Artificial Intelligence: A Modern Approach, fourth edition. The bookstore has the hardbound (aka US) edition. Used copies, third edition, paperback (aka international) and electronic editions are also fine. It is officially optional; everything critical should be in the posted notes.
You will also need a reference for Python, which we will use to write the MPs. A good place to start is the the Python Tutorial. You should install version 3.8. If you'd like a hardcopy reference for the basics, the hardcopy version 3.6 tutorial is still a good place to start because it covers features that haven't changed much.
Other supplementary readings will be posted, typically from textbooks and other resources available online.
Quizzes will will require a portable device. They will be browser-based, so a wide range of devices should work ok. However, it's best to have a real keyboard because you'll need to be able to type extended (e.g. 1-2 paragraph) answers.
As long as we have enough seats, it's ok for non-registered students to sit in on lectures. You can (obviously) also do MPs on your own. However, non-registered students may not take the quizzes.
Students may not add the class after add date (10 day of classes).
See the top menu for links to piazza, gradescope, and moodle.
If you registered at least a week before the start of classes, you should find that you are enrolled in the class on all three sites. The rest of you might or might not be on these sites yet, but you can add yourself. The moodle self-enrollment key is "Hedwig". The Gradescope access key is PXXDNV.
On the external sites (Gradescope and Piazza), please enroll using your illinois.edu email address. If you would prefer not to do this, e.g. for privacy reasons, contact the instructor to be added under an alternate email address. We need to be able to match your external email to the roster for purposes such as moving MP grades from Gradescope to Moodle.
The course will have 6 MPs, 6 quizzes, and a short final exam (aka Quiz 7).
Grading Formula (3 credit hours)
Students taking the course for 4 credit hours will also do two short literature review papers. The grading formula will be adapted as follows:
The translation into letter grades will be at least as generous as the standard high school scale. That is,
I may move these cutoffs downwards (i.e. raising the letter grades) if the raw scores seem to be running lower than I intended. However, historically, such adjustments have rarely been more than a couple percentage points. Because the work is different, the adjustments for the 4-hour students may differ from those for the 3-hour students.
Makeups for each quiz will be held in class on the next Friday after the regular sitting. You do not need special permission or documentation to take the makeup. Ad-hoc makeup times will be arranged only in rare cases (e.g. extended illness).
Since you have two weeks to do each MP, we expect you to have preliminary submissions well ahead of the deadline. Each MP deadline has a two-day grace period for managing most normal problems that may arise close to the deadline (e.g. short illness). The grace period will not be extended if you start the MP very late and then have some other problem arise. See below for discussion of major problems that may be beyond your control.
Regrade requests must be submitted within a week after the grade and feedback comments have been released. Regrade requests should be posted to the regrade folder on piazza. The course staff reserves the right to regrade not only the items questioned by the student, but also the other parts of the assignment or test.
You are encouraged to discuss assignments with other students, to share high-level understanding of the design (e.g. how is a perceptron supposed to work?) or basic utilities (e.g. how do I open a file in Python?). It is ok to conduct this discussion online, e.g. on piazza. However, extended fragments of code should be shown only to course staff. Programming and writing of reports/papers must be done individually.
Do not post or discuss details of MP or quiz solutions until you are sure that everyone else is done. In particular, wait until after the end of the MP grace period and after the makeup for a quiz. If you aren't sure, ask the instructor. Please do not post MP code on public sites such as public github repos.
You may look at external sources for tips and copy small fragments of code, e.g. examples of how to invoke some standard utility. Anything non-trivial copied from external sources must be properly acknowledged, e.g. using comments in your code. Be aware that these MPs are intended to be built largely from scratch, so your grade will be reduced if these external aides make the assignment significantly easier.
It is an academic integrity offense to deliberately or negligently copy from other students, assist other students in copying from you, or use external sources without acknowledgement. It is also an academic integrity offense if a written report significantly misrepresents what your code actually does. Copying with proper acknowledgement is not an academic integrity offence but may lead to a lowered grade if too little of the submitted work is your own. See the college statement and the student code for other types of actions that would be considered violations.
The standard penalty for an academic integrity violation is the larger of a 10% penalty or a zero on the assignments or quizzes involved. (This assumes a misdeed of some significance rather than a minor technical mistake or misunderstanding.) A second offense will typically cause you to fail the entire course.
If you need disability accommodations, please send a copy of your DRES letter to the instructor. Usually it's fairly easy to work out something appropriate. Similarly please tell the instructor if you need privacy protections beyond what we normally provide. (See here for the college's official statements.)
We expect that you can arrange your work so that minor problems (e.g. a short virus, planned travel) do not stop you from meeting the deadlines. In particular, you are expected to submit preliminary versions of MPs ahead of the deadline, so that last-minute problems will not have catastrophic consequences.
We will make special arrangements for the usual range of official excuses (e.g. illness, religious holidays), serious extenuating circumstances, and situations that you could not reasonably have avoided by good preparation (e.g. illness on the day of an exam/quiz). However, you must inform the instructor and respond to rescheduling emails in a timely manner. The meaning of "timely" depends on the circumstances. For example, planned travel or religious holidays should be reported in advance. On the other hand, there might be unavoidable delays informing us about a serious illness or injury.
For major and extended problems, we expect you to be in contact with the Dean of Students office. Or, for graduate students, your department's advising office. These offices can help document the problem, help you stay in contact with instructors, and determine if you need significant accommodations such as incompletes, late drops, light load..
Occasionally there are problems affecting a large number of people, e.g. network outages, snowstorms, TA strikes. In that case, we'll make appropriate adjustments. Watch for announcements (e.g. piazza). Do not make unsafe choices, e.g. driving into campus when the roads are dangerous.