Advanced Artificial Intelligence

I. Instructor Information

Instructor’s Name: Dr. Khaled Alrfou

Office hours: Sunday 11:00 AM – 1:00 PM

Appointments outside office hours: email me

TTU email address: khaled@stu.ttu.edu.jo

Contact information: Use email for the fastest response. Unless something unexpected occurs, I will reply to you within 24 hours.

II. Course Information

Course: Advanced Artificial Intelligence — 0602443

Prerequisite: 0602341 Artificial Intelligence

Course Description: This course covers advanced topics in artificial intelligence (AI) including planning, expert systems, fuzzy logic, nature-inspired algorithms (evolutionary computation and swarm intelligence), and learning from observations. Students will gain a firm grounding in techniques and component areas of AI and be able to apply this knowledge to develop intelligent systems.

Instructional Time

Additional instruction is provided through Moodle (recorded lecture videos, supplementary videos, discussion boards, and announcements/email).

Student Learning Outcomes

Describe heuristic search strategies and algorithms
Develop knowledge-based agents using logical systems
Implement agents that handle uncertainty using Probability and Utility Theory
Use Bayesian Networks to Moodle and solve problems
Describe how intelligent agents learn using machine learning algorithms

Program & Graduate Outcomes

Understand core principles of intelligent agents
Implement and evaluate search algorithms
Analyze AI system performance and trade-offs
Utilize ML algorithms and address overfitting and evaluation

GSLO1: Synthesize theoretical and research concepts.
GSLO2: Formulate creative responses to complex issues.

III. Required Course Materials

Textbook:

Artificial Intelligence: A Modern Approach (4th Edition) — Stuart Russell & Peter Norvig. Pearson, 2020. ISBN: 978-0134610993 (Required)

Supplemental readings, videos, and online materials: Posted on Moodle.

Hardware & software: Python development environment and a reliable internet connection.

IV. Instructional Methods and Activities

Modality: Face-to-face, in-person synchronous class.

V. Course Schedule (Tentative)

Topics#	Description	Reading
1	Course Overview
2	First-Order Logic / Inference in FOL	Ch. 1,2,7,8,9 Slides
3	Planning	Ch. 11
4	CSP	Ch. 6
5	Handling Uncertainty: Bayesian Networks	Ch. 12
6	Handling Uncertainty: Bayesian Networks	Chs. 13-13.3
7	Dynamic Bayesian Networks / Utility Theory	Chs. 14.1, 14.5
8	Decision Networks	Chs. 16-16.4
9	Decision Networks	Ch. 16.5
10	Machine Learning	Chs. 19.1-19.4, 19.7.1, 19.8.4, 19.9
11	Deep Learning	Ch. 21
12	Reinforcement Learning	Ch. 22
13	Natural Language Processing	Ch. 23
14	Transformer
15	Optimization Problems
16	Final Exam

*Schedule is tentative. Instructor reserves the right to modify the schedule. Changes will be announced verbally and via Moodle announcements.

VI. Grading Criteria & Course Policies

Course Grade

Average of Machine Problems: 20%

Midterm Exam: 30%

Final Exam: 50%

Policies

Turn in all assignments and take all scheduled tests by the due date. Extensions and make-up tests are not given except for special circumstances communicated promptly by email.
Under normal circumstances, late assignments receive zero.
Academic Honesty: Copying from other students, online sources (including generative AI), or past students results in zero for the assignment. Repeat offenses may result in failing the course.
Check Moodle regularly for announcements and materials. Lecture videos, assignments, and other course materials are posted on Moodle. All submissions must be via Moodle assignment area.

Getting Help & How to Succeed

If you need help, contact the instructor by email (listed above) or visit office hours. Start assignments early and seek help when stuck. I will normally reply to email within 24 hours.

Tips for success

Start on assignments early.
Ask for help if you are stuck.
View lecture videos—several times if necessary.
Read the textbook and review lecture slides.
Post questions on the discussion board.