| Contact Information | Course Description | Course Goals and Objectives |
| Course Outline | Calendar | Course Materials |
| Grading | Attendance and Participation | Assignments |
|
|
|
Contact Information
| Professor | Richard J. Povinelli, Ph.D. |
| Richard.Povinelli@mu.edu (checked late evening or early morning) | |
| Homepage | http://povinelli.eece.mu.edu |
| D2L | https://d2l.mu.edu/ |
| Phone | 288-7088 with voice mail |
| Office Hours | |
| Office | EN224 |
| Lab | EN523, EN388 |
Course Description and Prerequisites
This course provides a broad exposure to the field of artificial intelligence. Topics include intelligent agents, search, game playing, propositional logic and first-order predicate calculus, knowledge bases, planning, uncertainty, learning, communication and perception, and philosophical foundations.
Prerequisites: Data Structures.
Course Goals
- By the end of this course, you should...
- have a broad, general understanding of many of the areas that comprise the field of artificial intelligence (AI).
- be able to employ some of the methods from several areas within AI.
- be able to begin to understand and critique the AI literature.
Course Objectives
- By the end of this course, you should...
- Introduction
- be able to evaluate the various definitions of AI.
- be able to summarize the history of AI.
- Intelligent agents
- be able to provide a definition of a rational agent.
- be able to compare and contrast various agents including reflex, model-based, goal-based, and utility-based agents.
- be able to classify the environment in which a particular agent operates.
- Search
- be able to formulate a search problem.
- be able to evaluate a search algorithm on the basis of completeness, optimality, time complexity, and space complexity.
- be able to explain and contrast uniformed and informed searches.
- be able to compare, contrast, classify, and implement various search algorithms including breadth-first, uniform-cost, depth-first, depth-limited, iterative deepening, bidirectional, best-first, greedy, A*, RBFS, SMA*, hill-climbing, simulated annealing, and genetic algorithm searches.
- Game playing
- be able to provide a definition of a game.
- be able to evaluate, compare, and implement the minmax and alpha-beta algorithms, including for games of chance.
- be able to describe the current state-of-the-art game playing programs.
- Logics
- be able to describe the characteristics of a knowledge-based agent including its knowledge base and inference mechanism.
- be able to compare and contrast propositional logic and first-order predicate calculus.
- be able to employ propositional logic and first-order predicate calculus to design a knowledge-based agent.
- be able to analyze and employ logical inference in first-order logic.
- Planning
- be able to describe the basic representation for planning.
- be able to explain the partial order planning algorithm.
- Uncertainty
- be able to describe different types of uncertainty including degree of belief and degree of truth.
- be able to explain various probability constructs including prior probability, conditional probability, probability axioms, probability distributions, and joint probability distributions.
- be able to apply Bayes' rule.
- be able to apply belief networks to model a problem with uncertainty.
- be able to briefly describe other approaches to modeling uncertainty such as Dempster-Shafer theory and fuzzy sets/logic.
- be able to explain the utility theory axioms and the maximum expected utility principle.
- be able to assess various utility functions including multi-attribute utility functions.
- be able to design a decision network.
- be able to explain information value theory.
- be able to define a sequential decision problem.
- be able to explain the main ideas of game theory.
- Learning
- be able to describe a learning agent.
- be able to apply and analyze decision trees to learning problems.
- be able to determine the information gain provided by an attribute in a decision tree.
- be able to summarize computational learning theory.
- Natural language processing
- be able to describe the component steps of communication.
- be able to contrast formal and natural languages in the context of grammar, parsing, and semantics.
- Philosophical foundations
- be able to explain the incompleteness theorem and the halting problem and the limitations they describe for AI.
- be able to argue various philosophical positions for and against AI.
Course Outline
| What | When |
|
wk1-2 |
|
wk3 |
|
wk4 |
|
wk5 |
|
wk6-7 |
|
wk8 |
|
wk9-10 |
|
wk11-12 |
|
wk13 |
|
wk14 |
|
wk15 |
Calendar
| Week | Month | Tuesday | Thursday |
| 1 | September | 1 |
|
| 2 | September |
|
|
| 3 | September | 15 |
|
| 4 | September |
|
|
| 5 | September/October | 29 Review Critique 1 due |
|
| 6 | October | 6 |
|
| 7 | October |
|
|
| 8 | October |
|
|
| 9 | October |
|
|
| 10 | November | 3 Article Review 3 due |
|
| 11 | November |
|
|
| 12 | November |
|
|
| 13 | November | 24 |
|
| 14 | December |
|
|
| 15 | December | 8 |
|
| December |
|
|
| No Class |
NOTE: All dates and numbers are subject to change as deemed necessary!
November 20, 2009 is the final day for withdrawal with grade of W.
Course Materials
Required Texts
- Artificial Intelligence: A Modern Approach (2nd Edition) by Stuart J. Russell and Peter Norvig, Prentice Hall, 2003.
Grading
| What | Number | Value per | Total |
| Article Reviews | 4 | 20 | 80 |
| Review Critiques | 4 | 5 | 20 |
|
5 | 80 | 400 |
|
1 | 200 | 200 |
| Final | 1 | 300 | 300 |
| Total | 1000 |
NOTE: All dates and numbers are subject to change as deemed necessary!
Grade Scale
| 91+ | A |
| 89-91 | AB |
| 81-89 | B |
| 79-81 | BC |
| 71-89 | C |
| 69-71 | CD |
| 60-69 | D |
The grading scale is the most stringent one you will be held to, i.e. I can give you a higher letter grade than shown on the scale, but never a lower one.
Late Assignments
I will deduct 5% for assignments up to one day late, 10% for two days late, and 15% for up to three days late, and so on up to a maximum of 50% off. The weekend will count as 1 day. Assignments are due at the beginning of class. They are late after that. Assignments are not accepted after solutions have been distributed, nor after the last day of class. In class assignments are only accepted during the class period they are assigned.
Attendance and Participation
I have always enjoyed teaching classes where the students actively participate - a conversation is more fun than a monologue! Although there is no specific credit assigned for attending, it is still expected. There may be in class graded assignments. These may be turned in only during the class period they are given.
Assignments
You should expect to spend, on average, from twelve (12) to fifteen (15) hours on article reviews, critiques, reading, homeworks, and other preparation for this class. This time is in addition to the three (3) hours of lecture you are expected to attend every week.
All written portions of assignments must be created using a word processor (saved as Word 2003/2004 format). No part of the writeup may be hand drawn. The writeups are to be well written with proper spelling and grammar. Points will be deducted for poorly written and formatted assignments. Code and other portions should be submitted in the proper electronic format.
Only an electronic version of all assignments must be turned in. See the directions for instructions on how to turn in the assignments electronically. They are due according to the the time specified in the calendar.
Article Reviews
There will be four (4) article reviews. This will help you understand the relevant literature for your research project. You will identify articles that are relevant to the course topic, if you are unsure of its relevance double check with the instructor. For each article you will write a 1 page summary and a 1 page critique.
Peer Review of Article Reviews
Critiquing others work is an excellent mechanism for improving your own. It is backbone of the peer review process. You will be expected to evaluating others work including critiquing others article reviews.
Homeworks
There will be five (5) homeworks, which will be collected and graded. The homework assignments will be scaled to 400 points. The homeworks will be combinations of questions from the book and programming problems. You must cite, using IEEE format, your references including online ones.
Exams
There will be a midterm exam worth 200 points. There will be a final exam worth 300 points.
Dishonesty
College of Engineering Policy and Procedure - Academic Dishonesty (Make sure you read this)
Marquette University Policy - Academic Dishonesty (Make sure you read this)
My Policy
ACADEMIC DISHONESTY OF ANY FORM WILL NOT BE TOLERATED IN THIS CLASS. ANY STUDENT FOUND TO BE PERFORMING ANY ACT OF ACADEMIC DISHONESTY WILL BE SUBJECT TO THE MAXIMUM PENALTY FOR THE PARTICULAR OFFENSE.
I will not tolerate any form of dishonesty in any of my classes and I hope you feel the same. If you become aware of any form of dishonesty taking place in any activity concerned with any of your classes it is your duty to make sure that the offense is made known to the proper authority. This is a problem which affects all of us and I am asking for your help in keeping the standards of education here at Marquette University as high as they deserve to be.
Viruses
Any assignment turned in in electronic format that contains a virus will receive a zero.