Brief Course Description

This course will introduce the student to the fundamentals of artificial intelligence including the following topics:

  1. Search
    • classical search
    • adversarial search
    • constraint satisfaction
  2. Bayes Networks
    • Probability refresher
    • Bayes Networks
    • Hidden Markov Models
  3. Decision making under uncertainty
    • Markov Decision Processes
    • Reinforcement Learning
  4. Machine learning
    • Logistic Regression
    • Support vector machine
    • Backpropogation
    • k-means clustering, expectation maximization
    • Dimensionality Reduction

The course schedule is subject to change. See the schedule tab above.

Textbook

Artificial Intelligence: A Modern Approach, 3rd Ed., Russell and Norvig

Prerequisites

CS 2800 and CS 3500. In particular, it will be very important for you to have a working knowledge of discrete math and probability.

Academic Integrity

Cheating and other acts of academic dishonesty will be referred to OSCCR (office of student conduct and conflict resolution). See this link.

Lateness Policy

Late assignments will be penalized by 10% for each day late. For example, if you turned in a perfect homework assignment two days late, you would receive an 80% instead of 100%.

Instruction Staff

Primary Instructor: Robert Platt ( r [dot] platt [at] neu [dot] edu )
Office hours: Fridays, 11-12, 208B West Village H, or by Appt.

TA: Di Sun, sundi@ccs.neu.edu
Office hours: Mondays, 2--4pm, 214 West Village H

TA: Siyong Ma, ma.s@husky.neu.edu
Office hours: Tuesdays, 2:30--4:30pm, 208 West Village H

Announcements

None

Work Load

Required course work includes:

  • 5 Programming assignments (45% of your grade)
  • 3 Homework assignments (15% of your grade)
  • In class quizzes (10% of your grade)
  • 1 Midterm exam (10% of your grade)
  • 1 Final exam (20% of your grade) (only applies to students of CS5100)
  • 1 Final project (20% of your grade) (only applies to students of CS4100)

In-class Quizzes

Most class periods will be divided up into multiple concept segments. At the beginning of each segment, I will lecture on a particular topic. Then, students will answer a few short quiz questions (handed out at the beginning of class). Then, we will discuss the answers to the quiz and students will have an opportunity to change their answers. I will collect all quizzes at the end of class. Essentially, these quizzes are a proxy for measuring in-class engagement. Anyone who pays attention in class should receive full credit on these quizzes.

Programming assignments

We will use the Pacman AI projects developed at UC Berkeley. (John DeNero (denero@cs.berkeley.edu) and Dan Klein (klein@cs.berkeley.edu). For more info, see http://inst.eecs.berkeley.edu/~cs188/pacman/home.html. Used with permission.) There will be five programming assignments. All programming assignments must be completed using Python and are due at midnight on the day indicated on the schedule.

Homework assignments

There will be three written homework assignments due on the day indicated on the schedule.

Final project

CS4100 students must complete a final project instead of the final exam. The amount of project work should be equivalent to approximately two programming assignments. If they want, students my work in pairs. See schedule for due dates.