Course Links

home | course information | schedule | projects |

Course Information

Topics Covered

Agents, search, constraint satistfaction, game playing, utility theory, decision making under uncertainty, reinforcement learning, probabilistic reasoning, machine learning, and other topics as time permits.

Textbooks

Russell and Norvig, Artificial Intelligence, A Modern Approach. Prentice-Hall, third edition (a.k.a. the blue one). ISBN 0-13-604259-7. A copy is on reserve at the Computer Science Library in AVW 3164. We will also place on reserve in other libraries if requested.

You may, at your own risk, use the second edition (a.k.a. the green book). The second edition has most of what you need; the third edition has improved pseudocode and better sections on learning. The first edition (red) is too different to use.

Grading

Course Participation

Students are expected to attend lectures (see notes on excused absences below).  There will be occasional inclass exercises; participation in class discussions is encouraged.

Laptops are strongly discouraged during lecture. It is distracting both for the students around you, and for the lecturer. Given the early hour of the class, we will all need to be on our toes to keep things lively!

Programming

Python is an object-oriented language which should be accessible to students familiar with Java or Scheme. We do not expect you to have experience with Python, however we expect you to pick it up quickly. If you don't already have a TerpConnect account, please get one immediately, at http://www.oit.umd.edu/new. Go to How to use OIT's Unix Cluster for additional information.

Homeworks

Students will be allowed to work together on written homeworks. Students may discuss the homework to understand the problem and reach a solution. However, each student must write down the solution independently, and without referring to written notes from the joint session. In other words, each student must understand the solution well enough in order to reconstruct it by him/herself. In addition, each student should write on the problem set the set of people with whom s/he collaborated. This method as an experiment for CSMC421. If we find that people's homeworks are suspiciously similar (indicating copying as opposed to collaborative work), we will simply stop the experiment and disallow collaboration for the entire class.

Important note on the honor code: We occasionally reuse problem set questions from previous years' courses, we expect the students NOT to copy, refer to, or even look at the solutions in preparing their answers. It will be considered an honor code violation to intentionally refer to previous year's solutions (or other solutions available on the web) The purpose of problem sets in this class is to help you think about the material, not just give us the correct answers.

Late Homeworks

Unless otherwise stated, written homeworks are due at the start of class on their due date, and programming assignments are due electronincally at 11:59pm on their due date. Recognizing that students may face unusual circumstances and require some flexibility in the course of the semester, each student will have a total of seven free late (calendar) days to use as s/he sees fit. No additional individual extensions will be given. Once these late days are exhausted, any assignment turned in late will be penalized at the rate of 25% per late day (or fraction thereof). Under no circumstances will a homework or project be accepted more than four days after its due date. Late days are from 9:30AM to 9:30AM for written homeworks. Late homeworks should be handed in to the TA. If not available (e.g., on weekends), push it under Prof. Getoor's office door. In all cases, for late homeworks, students should write down the time that the homework is turned in and the number of late days used. It is a honor code violation to write down the wrong time.

Re-Grading Issues

The majority of the grading will be done by the TAs. If you think there has been a mistake in grading your homework or exam, please submit a regrade request to the TA explaining in writing — politely, precisely and concisely — the grading error that has occurred. Such request must be made no later than 1 week after the material in question was returned to the class. Any request to have an assignment regraded may result in the entire assignment in question being regraded, possibly resulting in a loss of points.

Academic Integrity

In this course you are responsible for both the University's Code of Academic Integrity and the University of Maryland Guidelines for Acceptable Use of Computing Resources. Any evidence of unacceptable use of computer accounts or unauthorized cooperation on tests, quizzes, or projects will be submitted to the Student Honor Council, which could result in an XF for the course, suspension, or expulsion from the University.

Excused Absences

Any student who needs to be excused for a prolonged absence (2 or more consecutive class meetings), the midterm or final exam must provide written documentation of the illness from the Health Center or from an outside health care provider. This documentation must verify dates of treatment and indicate the timeframe that the student was unable to meet academic responsibilities. No diagnostic information shall be given. Excused absences do not extend your 7 late day budget.

Any student eligible for and requesting reasonable academic accommodations due to a disability is requested to provide, to the instructor in office hours, a letter of accommodation from the Office of Disability Support Services (DSS) within the first two weeks of the semester.

Any student who must miss a class due to religious holidays should also notify the instructor during the first two weeks of class.

      last updated: