CS540 Introduction to Artificial Intelligence

CS540 section 1, Fall 2021
Department of Computer Sciences
University of Wisconsin–Madison


Course Information

Course learning outcomes: Students gain principles of knowledge-based search techniques; automatic deduction, knowledge representation using predicate logic, machine learning, probabilistic reasoning. Students develop applications in tasks such as problem solving, data mining, game playing, natural language understanding, and robotics.

Number of credits associated with the course: 3

How credit hours are met by the course: This class meets for two 75-minute class periods each week over the semester and carries the expectation that students will work on course learning activities (reading, writing, problem sets, studying, etc) for about 3 hours out of classroom for every class period. The syllabus includes more information about meeting times and expectations for student work.

Prerequisite: (COMP SCI 300 or 367) and (MATH 211, 217, 221, or 275) or graduate/professional standing or declared in the Capstone Certificate in Computer Sciences for Professionals.

Time: TR 11:00AM - 12:15PM

Location: NOLAND 132

Textbook: Artificial Intelligence: A Modern Approach (4th edition). Stuart Russell and Peter Norvig. Pearson, 2020. ISBN 978-0134610993. (textbook is optional, but may be useful)

Piazza: Link will be used for asynchronous discussion and announcements.

Canvas: Link will be used for homework submissions, grading, etc.

Course Objectives

  • Understand and be able to apply the foundational tools in Machine Learning and Artificial Intelligence: Linear algebra, Probability, Logic, and elements of Statistics.
  • Understand core techniques in Natural Language Processing (NLP), including bag-of-words, tf-idf, n-Gram Models, and Smoothing.
  • Understand the basics of Machine Learning. Identify and summarize important features in supervised learning and unsupervised learning.
  • Distinguish between regression and classification, and understand basic algorithms: Linear Regression, k-Nearest Neighbors, and Naive Bayes.
  • Understand the basics of Neural Networks: Network Architecture, Training, Backpropagation, Stochastic Gradient Descent.
  • Learn aspects of Deep Learning, including network architectures, convolution, training techniques.
  • Understand the fundamentals of Game Theory.
  • Understand how to formulate and solve several types of Search problems.
  • Understand basic elements of Reinforcement Learning.
  • Consider how Artificial Intelligence and Machine Learning problems are applied in Real - World settings and the Ethics of Artificial Intelligence.

Lecture Delivery

The regular lecture time slots are Tuesday and Thursday 11:00AM - 12:15PM CT.

Each lecture will be a series of short mini-lectures. The lecture will be divided into three blocks. In each block, the instructor will cover some content, and then deliver short quiz questions to clear up any confusion before proceeding to the next block. We would like, whenever possible, all students to participate in the quiz. We also plan to record the lecture and make it available afterwards to watch asynchronously outside of the lecture time. The students can ask questions anytime during the lecture and can post questions on Piazza after class.

Grading

The following weighted sum are used for the final average score:

  • Max{ 15% * Midterm Exam + 15% * Final Exam, 30% * Final Exam} 70% * Homework Assignments.

At the end of the semester, the final letter grades are given based on an approximate curve on the final average score. The weights placed on the assignments will be strictly enforced.

The final letter grade will be assigned based on the percentile of the final average score in the class:

  • A: Top 30-40% of the final score
  • AB: next 20-30%
  • B: next 10-20%
  • BC: next 0-20%
  • C: next 0-10%
  • D/F: 0-5%

As student performance may vary from semester to semester, the instructors reserve the right to adjust this distribution. McBurney Center students should contact the instructors to specify any special requests for the exams or homework assignments together with the supporting documentation provided by the McBurney Center. We will do our best to accommodate the requests.

Homework Policies

Homework assignments include written problems and programming (in Python). Frequently-asked questions (FAQs) on homework assignments will be posted on Piazza. Homework is always due on Canvas the minute before class starts on the due date. Late submissions will not be accepted. Assignment grading questions must be raised with the TAs within 72 hours after it is returned. Note that a regrading request for a part of a homework question may trigger the grader to regrade the entire homework and could potentially take points off. Regrading will be done on the original submitted work, no changes allowed.

TWO lowest homework scores are dropped from the final homework average calculation. This drop is meant for emergency usage. Additional drops, late days, or homework extensions will not be provided. We encourage you to use a study group for doing your homework. Students are expected to help each other out, and if desired, form ad-hoc homework groups. However, each student must produce and turn in their own, unique work.

Exams

There will be a midterm exam and a final exam. The form of the exams will be determined (online or in-person). Please plan for exams at these times and let us know about any exam conflicts during the first two weeks of the semester. If an emergency arises that conflicts with the exam times, email us as soon as possible. Emergency exam conflicts will be handled on a case-by-case basis.

If in-person exams:

  • Midterm: (Tentative) Oct 28, Thursday 11:00AM - 12:15PM; Exam room: lecture room NOLAND 132

  • Final: Dec 23, Thursday 2:45PM - 4:45PM; Exam room: TBA

Exam grading questions must be raised with the instructor within 72 hours after it is returned. If a regrade request is submitted for a part of a question on the exam, the grader reserves the right to regrade the entire exam and could potentially take points off.

Office Hours

Instructors / TAs / peer mentors will hold office hours in-person or online. See the Office Hours webpage for details.