Scribd
Upload
4 views

Course Outline Comp6721 W25

COMP6721 is an Applied Artificial Intelligence course offered in Winter 2025 at Concordia University, focusing on core AI concepts including machine learning and natural language processing. Students must have proficiency in Python and a strong understanding of probability and linear algebra. The course includes lectures, lab sessions, projects, and exams, with a grading scheme that emphasizes teamwork and practical application of AI techniques.

Uploaded by

badasscertified4
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
4 views

Course Outline Comp6721 W25

COMP6721 is an Applied Artificial Intelligence course offered in Winter 2025 at Concordia University, focusing on core AI concepts including machine learning and natural language processing. Students must have proficiency in Python and a strong understanding of probability and linear algebra. The course includes lectures, lab sessions, projects, and exams, with a grading scheme that emphasizes teamwork and practical application of AI techniques.

Uploaded by

badasscertified4
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

COMP6721 Applied Artificial Intelligence

Department of Computer Science and Software Engineering


Winter 2025

Lectures: Thu 17:45-20:15 Room: H 531 SGW


Instructor: Arash Azarfar [email protected]
Office hours: In person ER 1175 Thursday 16:30-17:30 or by Appointment

Coordinator: Dr. Sabine Bergler

* Office Hours:
Please send me an email at least a few hours in advance to confirm.

TA/Lab Demonstrators:
 Farzad Salajegheh
 Maryam Valipour
 Firat Oncel
 Rose Rostami

Students who have completed COMP 472 may not take this course for credit.

Objectives
The purpose of the course is to provide a broad technical introduction to the core concepts of
Artificial Intelligence (AI). Topics include state-space search (uninformed and informed/heuristic
search), adversarial search, Machine Learning (ML), Artificial Neural Networks (ANN), Deep
Learning (DL), Convolutional Neural Networks (CNN), knowledge graphs and representation, and
Natural Language Processing (NLP). It is intended as an overview or first introduction to AI,
as there are dedicated courses covering ML, DL, Computer Vision, CNN, NLP, Intelligent
Systems, and other areas of AI in more detail.

Specific Knowledge and Skills Needed for this Course:


To succeed in this course, you will need specific skills and knowledge in the following areas:
Programming Skills:
• Python: Proficiency in general programming using Python is essential for lab sessions
and the course project. A brief introduction to Python will be provided during the first lab
session, but pre-existing familiarity is strongly recommended.
Mathematical Foundations:
• Probability Theory: A strong understanding of probability is needed, particularly for
topics involving machine learning and decision-making algorithms.
• Linear Algebra: Concepts from linear algebra will be utilized frequently, especially in
machine learning and neural network modules.
If you find yourself lacking in any of these areas, you are strongly encouraged to review these
topics before the DNE (Did Not Enter) deadline.

Textbook
There is no single textbook that will be used for this course. For each lecture topic, required and
recommended readings will be posted as part of the lecture information on Moodle. Generally,
these readings will be available online or as an electronic resource through the Concordia Library.

Moodle Web Site


Amendments to this syllabus, if any, as well as other important information will be made available
through the course's Moodle site. The Moodle site also provides additional reading material, as
well as discussion forums for asking questions on lecture topics, projects, exams, etc. Note that you
must be registered for the course to access the Moodle (there is typically a one-day delay between
registering and receiving Moodle access).

Grading Scheme
The grading distribution is as follows:

25% Course Project(s) (two submissions, teamwork)


15% Assignments (two or three assignments, teamwork)
20% Midterm Exam
40% Final Exam
2% Bonus, Lab participation

Note that if your performance on the final exam exceeds that of the midterm, the midterm grade
may be waived, and the final exam will account for 60% of your overall grade.
Midterm Exam:
Please note that the course contains one midterm exam and will be taken during the lecture time in
class, in written form. There will be NO make-up session for retaking it.

Note: It is your responsibility to adhere to the university’s code of conduct as detailed in the
calendar. All students must read and sign the Expectations of Originality form and submit the
signed copy with their project deliverables.

Tentative Course Schedule

Week Topic Tentatively on


1 Course Introduction. Introduction to AI: Overview & History 16 January
2 State-Space Search: Uninformed & Heuristic Search 23 January
3 Adversarial Search: Mini-Max & Alpha-Beta Pruning 30 January
4 Introduction to Machine Learning, Naïve Bayes Classifier, Evaluation 6 February
5 ML: Decision Trees, Support Vector Machine (SVM) 13 February
6 ML: Ensemble Methods, Unsupervised Learning 20 February
7 Reading week 27 February
8 Midterm (Covering the first 6 lectures) 6 March
9 Introduction to Artificial Neural Networks (ANN) 13 March
10 Deep Learning, Convolutional Neural Networks, DL Optimization 20 March
11 Knowledge Graphs (I, II) 27 March
12 Natural Language Processing (NLP) 3 April
13 NLP: Vector Space Model, Applications, Deep Leaning for NLP 10 April

https://www.concordia.ca/academics/graduate/calendar/current/academic-calendar/current-academic-
calendar-dates.html

Laboratory Sessions
There are 11 laboratory sessions and 11 exercises in total posted each week. They are discussed
during the laboratory sessions. Note that lab sessions are a mandatory part of the course and take
place in-person. You must attend the lab section you are registered in.

The lab sessions start from the second week of the semester. The lab sessions cover the lecture
material from the previous lecture as well as the posted exercises. Before each lab, it is essential
that you review the previous week's lecture material, complete any assigned readings, and review
the corresponding lab exercises. While the lectures focus on theoretical concepts and algorithms,
the labs introduce new programming content not covered in the lectures. These sessions offer
hands-on experience with practical applications through various AI libraries and toolkits, such as
Python's scikit-learn and PyTorch.

Course Projects
As part of the course, you will work on two AI projects related to the topics covered in the lectures.
Complete guidelines for the course projects will be announced in class and on Moodle. The projects
are teamwork. The process of team formation should be started from the first class and confirmed
after the DNE deadline.

Programmer-On-Duty (POD) Sessions


The lab sessions are dedicated to discussing the predefined assignments. However, if time allows,
you could seek guidance in developing your course project.
POD sessions are specifically for programming and project-related questions where a
programming expert is available to answer the questions.

Email Inquiries
All inquiries related to the course must be communicated via email using the contact info below.
Your email subject line must follow a prefixed topic of “[COMP6721]”

Lecturer Arash Azarfar [email protected]


Lead TA/Lab Farzad Salajegheh [email protected]
TA/Lab/ Maryam Valipour [email protected]
TA/Lab/ Firat Oncel [email protected]
TA/Lab/ Rose Rostami [email protected]

Disclaimer
In the event of extraordinary circumstances beyond the University's control, the content and/or
evaluation scheme in this course is subject to change.

Course Learning Outcomes (CLOs):


By the end of this semester, students are expected to master the following skills and areas of
knowledge:

Critical Analysis: Ability to critically analyze different AI algorithms, evaluating their


appropriateness for various applications.
Data Interpretation: Develop skills in preprocessing and interpreting large datasets, making
them suitable for AI and machine learning models.
Algorithm Implementation: Gain hands-on experience in implementing, testing, and debugging
algorithms in a popular programming environment like Python.
Model Evaluation: Acquire the knowledge and skills to evaluate the performance of different AI
and machine learning models using various metrics.
AI System Design: Ability to design simple AI systems that incorporate elements of machine
learning, natural language processing, and/or deep learning algorithms.
Collaboration Skills: Gain experience in collaborative problem-solving and project
development, through the team project and lab sessions.
Comparative Analysis: Learn to compare and contrast the strengths and weaknesses of various
AI and machine learning approaches in different settings.
Application to Real-World Problems: Gain the ability to apply theoretical concepts in AI to real-world scenarios,
appreciating the complexities and constraints of actual implementations

Health and Safety Guidelines


General health and safety instructions and available health and safety trainings can be found at:
Safety Programs - Concordia University (https://www.concordia.ca/campus-life/safety/general-
safety.html)

On Campus Resources
Please visit Student services at Concordia University
(https://www.concordia.ca/ginacody/students/services.html ) for the services available to Gina
Cody School students.

You might also like