CSIS 440 Artificial Intelligence

Course Description

An introduction to the basic concepts and techniques of artificial intelligence (AI), knowledge representation, reasoning and problem solving, AI search techniques, and moral and ethical considerations related to the use of AI-based systems. AI solutions will be developed in an appropriate AI language.


Instructor

Brian R. Snider
Office hours: Wood-Mar 223 (see schedule)


Texts

required
recommended


Resources

Objectives

This course studies four main objectives of artificial intelligence (AI):

  1. Modeling the environment by constructing computational representations of the real world
  2. Perceiving and reasoning—obtaining and creating information (i.e., knowledge) to populate a computational representation
  3. Taking action—use the knowledge of the environment and desired goals to plan and execute actions
  4. Learning from past experience

Students will:

Course Organization

This course consists of lectures, group discussions, and hands-on programming exercises. Programming assignments will be carried out in the Prolog and Python programming languages. Some instruction in the use of these languages will be provided during lecture; however, I expect that you will consult additional resources to supplement your knowledge.

The course will include regular homework and/or programming assignments. There will be no credit given for late assignments (without an excused absence)—turn in as much as you can. Unless otherwise specified, no handwritten work will be accepted.

Reading should be completed before the lecture covering the material per the provided schedule. Not all reading material will be covered in the lectures, but you will be responsible for the material on homework and exams. Quizzes over the assigned reading may be given at any time.


Collaboration and Academic Integrity

See the GFU CS/IS/Cyber policies for collaboration and discussion of collaboration and academic integrity. See also the university's policy on the use of generative AI and related tools in an academic setting. Most students would be surprised at how easy it is to detect collaboration or other academic integrity violations such as plagiarism in programming—please do not test us! Remember: you always have willing and legal collaborators in the faculty. We encourage you to ask questions in class, ask for help in the CS lab, use the class mailing list, and visit office hours for assistance.

Unless otherwise specified (e.g., for a group assignment or project), you are expected to do your own work. This also applies to the use of online resources (e.g., solution guides), help forums (e.g., StackOverflow), and generative models (e.g., ChatGPT). Put simply: if you are representing someone (or something) else's work as your own, you are being dishonest. Any suspected incidents of academic integrity violations will be investigated and reported to the Academic Affairs Office as they arise.

Almost all of life is filled with collaboration (i.e., people working together). Yet in our academic system, we artificially limit collaboration. These limits are designed to force you to learn fundamental principles and build specific skills. It is very artificial, and you'll find that collaboration is a valuable skill in the working world. While some of you may be tempted to collaborate too much, others will collaborate too little. When appropriate, it's a good idea to make use of others—the purpose here is to learn. Be sure to make the most of this opportunity but do it earnestly and with integrity.


University Resources

Accessibility and Disability

If you have specific physical, psychiatric, or learning disabilities and require accommodations, please contact Disability & Accessibility Services (DAS) as early as possible so that your learning needs can be appropriately met. For more information, go to georgefox.edu/das or contact das@georgefox.edu.

My desire as a professor is for this course to be welcoming to, accessible to, and usable by everyone, including students who are English-language learners, have a variety of learning styles, have disabilities, or are new to online learning systems. Be sure to let me know immediately if you encounter a required element or resource in the course that is not accessible to you. Also, let me know of changes I can make to the course so that it is more welcoming to, accessible to, or usable by students who take this course in the future.

Academic Resource Center

The Academic Resource Center (ARC) on the Newberg campus provides all undergraduate students with free writing consultation, academic coaching, and learning strategy review (e.g., techniques to improve reading, note-taking, study, time management). The ARC offers in-person appointments; if necessary, Zoom appointments can be arranged by request. The ARC, located on the first floor of the Murdock Library, is open during the academic year from 1:00–9:00 p.m., Monday through Thursday, and 12:00–4:00 p.m. on Friday. To schedule an appointment, click on the TracCloud icon on the Canvas dashboard, go to traccloud.georgefox.edu, call 503-554-2327, email the_arc@georgefox.edu, or stop by the ARC. Visit arc.georgefox.edu for information about ARC Consultants' areas of study, instructions for scheduling an appointment, learning tips, and a list of other tutoring options on campus.

Student Support Network

George Fox University uses a robust referral and support system, Fox360, to learn about students who are experiencing various student success concerns. Students who are referred by a professor, other employee, or fellow student will be contacted by a member of our Student Support Network to explore the student's situation, develop a plan, and connect with relevant campus resources. GFU community members who have a concern about a student's well-being can submit an alert by going to fox360.georgefox.edu. Our goal is to provide 360° care for students as they navigate their college experience. For more information see ssn.georgefox.edu or contact Rick Muthiah, Director of Learning Support Services.


Health and Safety Considerations

Please review the entirety of the university's official COVID-19 web page for the most up-to-date community guidance.

Grading

Grading Scale

The final course grade will be based on:

Graded course activities will be posted to Canvas. Take care to read the specifications carefully and proceed as directed. Failure to pay attention to detail will often result in few to zero points being awarded on a given activity.

Grades will be updated as often as possible; you are encouraged to use the "What-If" functionality to calculate your total grade by entering hypothetical scores for various items.

Note that some graded activities in this course will be submitted via GitLab.

Tentative Schedule

Week 1 · Tue

Introduction and History

AIMA: Ch. 1

Week 1 · Thu

Agents and Environments

AIMA: Ch. 2.1–2.3; Ch. 27.1
Mitchell: Prologue

Week 2 · Tue

Agent Structure; Philosophy of AI

AIMA: Ch. 2.4; Ch. 27.2
Mitchell: Ch. 1–3

Week 2 · Thu

Problem Solving

AIMA: Ch. 3.1–3.3
Mitchell: Ch. 4

Week 3 · Tue

Blind Search

AIMA: Ch. 3.4; Ch. 27.3
Mitchell: Ch. 5–6

Week 3 · Thu

Heuristic Search

AIMA: Ch. 3.5–3.6
Mitchell: Ch. 7

Week 4 · Tue

Local Search and Optimization

AIMA: Ch. 4.1

Week 4 · Thu

Online Search

AIMA: Ch. 4.5

Week 5 · Tue

Adversarial Search

AIMA: Ch. 5.1–5.4
Mitchell: Ch. 8

Week 5 · Thu

Stochasticity and Partial Observability

AIMA: Ch. 5.5–5.7

Week 6 · Tue

Constraint Satisfaction

AIMA: Ch. 6.1–6.2
Mitchell: Ch. 9

Week 6 · Thu

Mid-semester break—no classes

Week 7 · Tue

Knowledge-Based Agents

AIMA: Ch. 7.1–7.2

Week 7 · Thu

Propositional Logic

AIMA: Ch. 7.3–7.4
Mitchell: Ch. 10

Week 8 · Tue

Propositional Logic-Based Agents

AIMA: Ch. 7.7

Week 8 · Thu

Midterm exam

AIMA: Ch. 1–7
Mitchell: Ch. 1–7

Week 9 · Tue

First-Order Logic

AIMA: Ch. 8
Mitchell: Ch. 11

Week 9 · Thu

First-Order Inference

AIMA: Ch. 9

Week 10 · Tue

Knowledge Representation

AIMA: Ch. 10.1
Mitchell: Ch. 12

Week 10 · Thu

Planning

AIMA: Ch. 11.1–11.3

Week 11 · Tue

Machine Learning

AIMA: Ch. 19.1–19.5
Mitchell: Ch. 13

Week 11 · Thu

Machine Learning Models and Systems

AIMA: Ch. 19.6–19.9

Week 12 · *

Spring break—no classes

Week 13 · Tue

Deep Learning and Deep Neural Networks

AIMA: Ch. 21.1–21.2
Mitchell: Ch. 14

Week 13 · Thu

DNN Architectures, Algorithms, and Techniques

AIMA: Ch. 21.3–21.8

Week 14 · Tue

Selected Topics: Natural Language Processing

AIMA: Ch. 23
Mitchell: Ch. 15

Week 14 · Thu

Selected Topics: Deep Learning for NLP

AIMA: Ch. 24

Week 15 · Tue

Selected Topics: Robotics

AIMA: Ch. 26
Mitchell: Ch. 16

Week 15 · Thu

Future of Artificial Intelligence

AIMA: Ch. 27

Week 16 · TBD

Final exam

AIMA: *
Mitchell: *
  1. GFU
  2. CSIS
  3. BRS
  4. CSIS 440

This page was last modified on 2024-03-04 at 17:17:38.

Copyright © 2015–2024 George Fox University. All rights reserved.