King Fahd University of Petroleum & Minerals

College of Computing and Mathematics

Computer Engineering Department

COE 292: Introduction to Artificial Intelligence (3-0-3)

Syllabus – Fall Semester 2022-2023 (221)
Introduction
This course is intended to provide an opportunity to learn and develop the necessary knowledge and skills to
understand the basic Machine Learning and Artificial Intelligence techniques used to solve real work problems. The
course is intended for all KFUPM students in the sophomore level. It is designed as a full semester three credit course
that combines all essential elements of enabling students digitally and is the last of the digital enabler courses you will
take during your academic career. COE292 class specifically focuses on learning and engaging with fundamental
information and tools that will provide you the basis for understanding and applying artificial intelligence techniques
in your future carrier.
Website: Blackboard
Class Time and Venue: Click here
Course Catalog Description
Introduction to AI; Uninformed vs. informed search. Constraint satisfaction. Logic and Reasoning pattern;
Propositional Logic; Reasoning Patterns. Supervised learning using Nearest Neighbor and SVM. Clustering with
mean-shift algorithm. Overview of Neural Networks and training. Overview of deep learning and applications. Feature
extraction techniques in Computer Vision. Applications in reinforcement learning.
Course Objectives
The objectives of this course are to:
1. Introduce students to the field of artificial intelligence.
2. Learn a suite of AI tools and their representation.
3. Apply AI tools to model and solve problems.
Course Learning Outcomes
Upon completion of the course, you should be able to:
1. Understand the meaning of AI, its alternative approaches, and the implications of AI for cognitive science
more broadly.
2. Understand basic search algorithms and their uses in solving problems.
3. Learn and apply basic AI algorithms, techniques, and representation methods to a variety of real-world
problems.
Textbooks and Material
• Lecture Handouts.
• Chowdhary, K.R., Fundamentals of Artificial Intelligence, Springer, 2020. (ISBN 978-81-322-3972-7)
• Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, Pearson (Third Edition) 2016.
Assessment Plan

Assessment Tool Weight

Assignments 15%
Quizzes 15%
Midterm Exam (29 October at 7:00pm) 35%
Final Exam (scheduled by the registrar) 35%
Lecture Schedule:

Week Lecture Notes

1 Introduction to AI: topic include history, and example of
use of AI in practical applications.
2 Goal Trees: topic include problem solving using tree
structure and generate and test algorithm
3 Search Methodologies: Uninformed search such as Depth
First Search (DFS), Breadth First Seach (BFS) and
Uniform Cost Search (UCS).
4 Search Methodologies: Informed search such as A*
Search.
5 Search Methodologies: Adversarial Search using the
Mini-Max technique
6 Introduction to Logic: Logic and Reasoning pattern,
Introduction to logic and its use in AI.
7 Constraint Satisfaction Problems: that will include
Introduction and examples, Search Results, Solving
Constraint Satisfaction Problems (CSP) formulation and
Basic strategies for solving CSPs.
8 Application Areas of AI using Machine Learning (ML):
that will include example of supervised learning using
Nearest Neighbor and Support Vector Machine (SVM).
Unsupervised learning using with Mean-shift algorithm.
9 Application Areas of AI using Machine Learning (ML):
that will include example of supervised learning using
Nearest Neighbor and Support Vector Machine (SVM).
Unsupervised learning using with Mean-shift algorithm.
10 Application Areas of AI using Machine Learning (ML):
that will include example of supervised learning using
Nearest Neighbor and Support Vector Machine (SVM).
Unsupervised learning using with Mean-shift algorithm.
11 Application Areas of AI using Reinforcement Learning
(RL): that discusses what is RL, how RL works, RL
algorithms, types of RL and RL verses supervised learning
and RL applications.
12 Application Areas of AI using Neural Networks (NN):
that will give overview of NN, how to train the NN.
13 Application Areas of AI using Neural Networks (NN):
that will give overview of NN, how to train the NN.
14 Application Areas of AI using Neural Networks (NN):
that will give overview of NN, how to train the NN.
15 Application of Deep learning
Course Policies

• Course Website & Participation: Students are required to periodically check the course website on Blackboard
and download course material as needed. Several resources will be posted through the website as well. Keys to
exams are generally discussed during class as time permits but solutions will not be posted. A common
Blackboard will be used for communication and interaction, posting, and submitting assignments, posting grades,
posting sample exams, etc. It is expected that you get benefit of the discussion board by raising questions or
answering questions put by others. Your active participation and the usefulness of the material you share with
other students will be rewarded.
• Attendance: Regular attendance is a university requirement; hence attendance will be checked each lecture.
Missing more than 9 lectures will result in a DN grade without warning. To avoid being considered as absent, an
official excuse must be shown no later than one week of returning to classes.
• No makeup of quizzes or exams will be given.
• Re-grading policy: If you have a complaint about any of your grades, discuss it with the instructor no later than
a week of distributing the grades (except for the final). Only legitimate concerns on grading should be discussed.
• Office Hours: Students are encouraged to visit faculty in the office hours to clarify any part of the material that
is not clear.
• Academic honesty: Students are expected to abide by all the university regulations on academic honesty.
Cheating will be reported to the Department Chairman and will be severely penalized. Although collaboration
and sharing knowledge is highly encouraged, copying others’ work (classmates, others or from the web) without
proper citation, either in part or full, is considered plagiarism. Whenever in doubt, review the university guidelines
or consult the instructor. Cheating in whatever form will result in an F grade.
• Normalization will be applied to grades only for each instructor to ensure fairness across different instructors. For
normalization, we will use the 𝑧-score to ensure that the distribution of grades follows a similar distribution with
a unified mean and standard deviation that will be chosen by the instructors later. The 𝑧-score captures an
individual performance relative to the population's mean and variance. The normalization score will be calculated
as: 𝑧 = (𝑋 − 𝑀)/𝑆 where: 𝑧 refers to the 𝑧-score, 𝑀 is the estimate of the population's mean, 𝑆 is the estimate of
the population's standard deviation, and 𝑋 is an individual score within the distribution having mean 𝑀 and
standard deviation 𝑆.
 Class Time and Venue

Sec. Time Venue Instructor Office Office Hours

Mustafa Ghaleb
01 UTR 0800-0850 59-1005
(mustafa.ghaleb@kfupm.edu.sa)
Aiman El-Maleh MW 11:00 – 11:59 am
03 UTR 0900-0950 22-132 22/407-5
(aimane@kfupm.edu.sa) By Appointment via email
Akram Ahmed MW 11:00 – 11:59 am
04 UTR 0900-0950 59-2015 22-207
(akram@kfupm.edu.sa) By Appointment via email
Abduljabbar Siddiqui
05 UTR 1000-1050 24-151 22/208
(abduljabbar.siddiqui@kfupm.edu.sa)
Ahmed Al-Mulhem
06 MW 0930-1045 22-134 22/407-2
(ahmadsm@kfupm.edu.sa)
Akram Ahmed MW 11:00 – 11:59 am
07 UTR 1100-1150 24-125 22/207
(akram@kfupm.edu.sa) By Appointment via email
Akram Ahmed MW 11:00 – 11:59 am
08 UTR 0800-0850 59-2002 22/207
(akram@kfupm.edu.sa) By Appointment via email
Kamal Chenaoua MW 11:00 am – 12:00 pm
09 UTR 1200-1250 59-1003 23/082
(cskamel@kfupm.edu.sa) By Appointment via email
Abduljabbar Siddiqui
10 UTR 1200-1250 59-2021 22/208
(abduljabbar.siddiqui@kfupm.edu.sa)
Ahmed Al-Mulhem
11 MW 1100-1215 22-125 22/407-2
(ahmadsm@kfupm.edu.sa)
MW 10:00 – 10:59 am
Rashad Othman
12 UTR 1300-1350 59-1003 62/213 By Appointment via email
(othmanr@kfupm.edu.sa)

Kamel Chenaoua
13 UTR 1000-1050 24-240 23/082
(cskamel@kfupm.edu.sa)
Abdulaziz Barnawi
14 UTR 1200-1250 59-2009 22/407-4
(barnawi@kfupm.edu.sa)
Abdulaziz Barnawi
15 UTR 1000-1050 59-1005 22/407-4
(barnawi@kfupm.edu.sa)