CPSC 470/570 Artificial Intelligence

INSTRUCTOR

Dragomir Radev

SHORT DESCRIPTION

Introduction to Modern Artificial Intelligence

Topics include Intelligent Agents, Search and Problem Solving, Logic and Language, Reasoning and Uncertainty, and Learning

PRINCIPAL READING

Artificial Intelligence, A Modern Approach
Russell and Norvig
Third Edition (2009/2010)
Prentice Hall
ISBN: 0-13-604259-7 
http://aima.cs.berkeley.edu/

WEEKLY READING WORKLOAD

30-50 pages of the textbook

TYPE OF INSTRUCTION

Lecture

WEEKLY MEETINGS

COURSE ASSIGNMENTS (tentative)

• Project 0: Introduction to the Course Environment
• Project 1: Mathematical Models (problem set)
• Project 2: Search (Pacman)
• Project 3: Game Playing (Othello)
• Midterm
• Project 4: Language and Logic (Deep Learning and NLP)
• Project 5: Classification (Autonomous Cars)
• Project 6: Reinforcement Learning (AI Gym)
• Final

MAIN GOALS OF THE COURSE

1. Learn the basic principles and theoretical issues underlying artificial intelligence
2. Understand why artificial intelligence is difficult
3. Learn techniques and tools used to build practical, realistic, robust AI systems
4. Understand the limitations of these techniques and tools
5. Gain insight into some open research problems in AI

DISTRIBUTION REQUIREMENTS

PREREQUISITES

(CPSC 201 and CPSC 202) or permission of the instructor. All assignments are in Python.

TOPICS

1. Introduction

   Introduction to AI, Python for AI, Agent-based view of AI

2. Problem Solving and Search

   Problem Solving and Search, Informed Search, Heuristic Search, Advanced Search, Game Playing, Adversarial Search, Genetic Algorithms, Constraint Satisfaction, Planning (if time)

3. Language and Logic

   Logical Agents, Predicate Logic, First Order Logic, Inference, Knowledge Representation, Natural Language Processing and Communication, Speech Processing (if time)

4. Reasoning under Uncertainty

   Quantifying Uncertainty, Intro to uncertainty, Probabilistic Reasoning, Bayesian Networks

5. Learning

   Learning from Examples, Classification and Clustering, Markov Decision Processes, Neural Networks, Reinforcement Learning, Autonomous Cars

SYLLABUS

Introduction to AI
Programming Languages for AI
Agent-based view of AI
Problem solving and search
Informed Search
Heuristic search
Adversarial search
Genetic algorithms
Constraint satisfaction
Intro to Logic and Logical agents
Propositional Logic
First order logic
Inference in FOL
Knowledge representation
Intro to Communication and Perception
Intro to uncertainty
Probabilistic reasoning
Bayesian Networks
Supervised Learning
Probabilistic reasoning over time (HMM+MDP)
Natural Language Processing and Speech
Neural networks, Deep Learning
Reinforcement learning
Autonomous cars
Conclusion

ACADEMIC HONESTY

Unless otherwise specified in an assignment all submitted work must be your own, original work. Any excerpts, statements, or phrases from the work of others must be clearly identified as a quotation, and a proper citation provided. Any violation of the University's policies on Academic and Professional Integrity may result in serious penalties, which might range from failing an assignment, to failing a course, to being expelled from the program.

Violations of academic and professional integrity will be reported to Student Affairs. Consequences impacting assignment or course grades are determined by the faculty instructor; additional sanctions may be imposed.