CMPSC 442 Spring 2024: Artificial Intelligence

Course Information

Instructor Lecture Time and Location TA Course Syllabus

Course Goals and Objectives

This course provides an overview of the foundations, problems, approaches, implementation, and applications of artificial intelligence. Topics covered include problem solving, goal-based and adversarial search, logical, probabilistic, and decision theoretic knowledge representation and inference, decision making, and learning. Through programming assignments that sample these topics, students acquire an understanding of what it means to build rational agents of different sorts as well as applications of AI techniques in language processing, planning, vision. The goal of this course is to learn
  1. Basic techniques for building intelligent computer systems
    1. Search, (games,) constraint satisfaction, uncertainty and probability, Bayes Rule, Naïve Bayes, Hidden Markov Models
    2. Introduction to fundamental concepts in machine learning: linear regression, linear regression classifier, perceptron learning rule
  2. In depth consideration of the role AI will play in our lives

Prerequisites

Enforced Prerequisite at Enrollment: CMPSC 221. Enforced Concurrent at Enrollment: CMPSC 465. Students are expected to have a good understanding of probability, data structures, and programming. We will cover Python basics early in the semester. Students should feel comfortable programming, debugging, and testing in Python.

Textbook

Programming Assignments

There are 6 programming assignments. The programming assignments shall be done with Python 3.6+. Every programming assignment will be graded by an autograder. Do not submit with import errors or syntax errors. You must use the template *py files. Your code must produce a correct or partly correct answer to get full or partial credit. All submissions must be your own dependent work. Do not copy other people's code or misrepresent it as yours. We will use high grade plagiarism detection code. Late Policy for Programming Assignments. There is only 1 late day allowed with a penalty of 25% for EACH programming assignment. For example, if you obtain a raw score 90 on the first late day, you will get 90x75%= 67.5; if you submit two days after the deadline, the score is 0.

Course Schedule

Date Topic Material / Reading Event Due
Week 1
Tuesday Jan 9
Introduction
[slides]
Thursday Jan 11 Intelligent Agents
[slides]
Week 2
Tuesday Jan 16
Search
[slides]
HW 1 Out
Thursday Jan 18
Search
[slides]
Week 3
Tuesday Jan 23
Search
[slides]
Thursday Jan 25 Game
[slides]
Week 4
Tuesday Jan 30
Game
[slides]
HW 1 Due
Thursday Feb 1 Game
[slides]
HW 2 Out
Week 5
Tue Feb 7
Constraint Satisfaction Problem
[slides]
Thursday Feb 8 Constraint Satisfaction Problem
[slides]
Week 6
Tuesday Feb 13
Logic Agents
[slides]
Thursday Feb 15 Logic Agents
[slides]
HW 2 Due
Week 7
Tuesday Feb 20
Logic Agents
[slides]
HW 3 Out
Thursday Feb 22 Probabilistic Agents
[slides]
Week 8
Tuesday Feb 27
Probabilistic Agents
[slides]
Tuesday Feb 29 Probabilistic Agents
[slides]
Week 9
Tuesday March 5
Spring Break
Thursday March 7 Spring Break
Week 10
Tuesday March 12
Hidden Markov Models
[slides]
HW 3 Due
Thursday March 14 Hidden Markov Models
[slides]
HW 4 Out
Week 11
Tuesday March 19
Hidden Markov Models
[slides]
Thursday March 21 Markov Decision Processes
[slides]
Week 12
Tuesday March 26
Markov Decision Processes
[slides]
Thursday March 28 Markov Decision Processes
[slides]
HW 4 Due
Week 13
Tuesday April 2
Machine Learning
[slides]
HW 5 Out
Thursday April 4 Machine Learning
[slides]
Week 14
Tuesday April 9
Machine Learning
[slides]
Thursday April 11 NLP, LLM, Generative AI
[slides]
HW 5 Due
Week 15
Tuesday April 16
NLP, LLM, Generative AI
[slides]
HW 6 Out
Thursday April 18 NLP, LLM, Generative AI
[slides]
Week 16
Tuesday April 23
AI Ethics
[slides]
Thursday April 25 AI Ethics
[slides]
HW 6 Due
TBD Final Exam Due