TORONTO METROPOLITAN UNIVERSITY

Course Outline (W2026)

ELE888: Intelligent Systems

Instructor(s)Dr. Mohammed Saif [Coordinator]
Office: EPH417
Phone: TBA
Email: mohammed.saif@torontomu.ca
Office Hours: Thursday 4:00 pm- 5:00 pm
Calendar DescriptionMachine learning and pattern classification are fundamental blocks in the design of an intelligent system. This course will introduce fundamentals of machine learning and pattern classification concepts, theories, and algorithms. Topics covered include: Bayesian decision theory, linear discriminant functions, multilayer neural networks, classifier evaluation, and an introduction to unsupervised clustering/grouping, and other state-of-the-art machine learning and AI algorithms.
PrerequisitesELE 532 or MEC 733
Antirequisites

None

Corerequisites

None

Compulsory Text(s):
  1. There are no required textbooks for this course. All of the material to be learned will be self-contained in the lecture notes that the instructor will provide as well as supplemental material to reinforce the concepts.
Reference Text(s):
  1. R. O. Duda, P. E. Hart and D. G. Stork, Pattern Classification, 2nd edition, John Wiley & Sons, 2002. ISBN: 0-471-05669-3.
Learning Objectives (Indicators)  

At the end of this course, the successful student will be able to:

  1. Generates solutions for complex engineering design problems (4b)
  2. Demonstrate iterative design process in complex engineering projects (4c)
  3. Construct effective arguments and draws conclusions using evidence. Write and revise documents using appropriate discipline specific conventions. Adapt format, content, organization, and tone for various audiences. Demonstrate accurate use of technical vocabulary. (7a)
  4. Construct effective arguments and draw conclusions using evidence. Write and revise documents using appropriate discipline specific conventions. Adapt format, content, organization, and tone for various audiences. Use graphics to explain, interpret, and assess information. (7c)
  5. Discuss the factors in decision making in the design of intelligent systems by principles and examples. Explain the impact of decisions and activities on the environment. (9a)
  6. Assess ethical risks and evaluates situations and actions in terms of the professional code of ethics for engineers. Evaluate competing values in decision making, and analyzes components of a decision in terms of professional codes of ethics and other ethical guidelines and to make decisions correspondingly. (10a)
  7. Investigate and communicate recent developments in a selected topics in intelligent system design. Critically evaluate the procured information for authority, currency and objectivity and make accurate and appropriate use of technical literature. (12b)

NOTE:Numbers in parentheses refer to the graduate attributes required by the Canadian Engineering Accreditation Board (CEAB).

Course Organization

3.0 hours of lecture per week for 13 weeks
1.0 hours of lab per week for 12 weeks
0.0 hours of tutorial per week for 12 weeks

Teaching Assistants1- Sarah Kamoun, email: skamoun@torontomu.ca
 2- Osama Harmouche, email: oharmouche@torontomu.ca
 3- Syed Ammad Ali Shah, email: s10shah@torontomu.ca
 4- Erfan Shahab, email: erfan.shahab@torontomu.ca
Course Evaluation
Theory
Midterm Exam 30 %
Quizzes (There is no quiz in course) 0 %
Final Exam 40 %
Laboratory
Lab Reports 30 %
TOTAL:100 %

Note: In order for a student to pass a course, a minimum overall course mark of 50% must be obtained. In addition, for courses that have both "Theory and Laboratory" components, the student must pass the Laboratory and Theory portions separately by achieving a minimum of 50% in the combined Laboratory components and 50% in the combined Theory components. Please refer to the "Course Evaluation" section above for details on the Theory and Laboratory components (if applicable).


ExaminationsMidterm exam, two hours, closed book (covers weeks 1-6).
 Final exam, during exam period, three hours, closed-book (covers all course materials).
Other Evaluation InformationLaboratories
 
 There are 4 practical assignments in this course. These are to be done individually and handed in
 electronically online. These assignments are more like mini-projects and are NOT meant to be
 done/completed in the assigned lab hours. They are to be done primarily outside lab hours.
 The assigned lab hours are available for you to make use of as you see fit and will also be the best time to get direct help from the TA on these assignments. In addition, you will need to demonstrate your lab works to the TA. The assignments will consist of theoretical and practical parts and will require use of Python.
Teaching MethodsThe course is delivered in person. All communications are online. All course materials are provided on the course shell.
Other InformationThe Course Outline is tentative. Please refer to the course shell for the most up-to-date details.
 
 Students may use Generative AI (e.g. ChatGPT, Grammarly, Perplexity, DeepL Translator) for ideation and brainstorming but not for research or for writing anything (e.g., lab reports) that will be submitted for credit. Failure to stay within these limits will be considered a breach of Policy 60.
 

Course Content

Week

Hours

Chapters /
Section

Topic, description

1

3

Introduction and General Concepts of Machine Learning and AI systems


2

3

Linear Algebra Review. Optimization and Gradient Descent. Review of Probability Concepts


3

3

Bayesian Decision Theory. Bayes Theorem and Decision Rule. Minimum Risk Action. Discriminant
 Functions. Gaussian Distributions.


4

3

Bayesian Decision Theory (continued).


5

3

Linear Discriminant Functions


6

3

Linear Discriminant Functions/Algorithms


8

3

Midterm


9

3

Logistic Regression and Softmax Regression


10

3

Introduction of Multilayer Neural Networks and Deep Learning


11

3

Neural Networks Continued. Advice on using Neural
 Networks. Introduction to Support Vector Machines: Cost Function
 Kernels Optimizing Cost Function.
 Advice on Applying Machine Learning Algorithms. Bias and Variance.
 Learning Curves. Machine Learning System Design. Error Analysis.
 Classifier Evaluation.


12

3

Introduction to Unsupervised Learning and algorithms such as K-means, NN Clustering


13

3

Principal Component Analysis


14

3

Final Review/Final Exams


Laboratory(L)/Tutorials(T)/Activity(A) Schedule

Week

L/T/A

Description

1-2

Lab 0

Lab Assignment 0: Intro to Python for Machine Learning

3, 4, 5

Lab 1

Lab Assignment 1: Bayesian Decision Theory

6, 8

Lab 2

Lab Assignment 2: Linear Discriminant Function

9-10

Lab 3

Lab Assignment 3: Multilayer Neural Network  

11-12

Lab 4

Lab Assignment 4: Unsupervised Learning

University Policies & Important Information

Students are reminded that they are required to adhere to all relevant university policies found in their online course shell in D2L and/or on the Senate website

Refer to the Departmental FAQ page for furhter information on common questions.

Important Resources Available at Toronto Metropolitan University

Lab Safety (if applicable)

Students are to strictly adhere and follow:

  1. The Lab Safety information/guidelines posted in the respective labs,
  2. provided in their respective lab handouts, and
  3. instructions provided by the Teaching Assistants/Course instructors/Technical Staff.

During the lab sessions, to avoid tripping hazards, the area around the lab stations should not be surrounded by bags, backpacks etc, students should place their bags, backpacks etc against the walls of the labs and/or away from their lab stations in such a way that it avoids tripping hazards.

Accessibility

Academic Accommodation Support

Academic Accommodation Support (AAS) is the university's disability services office. AAS works directly with incoming and returning students looking for help with their academic accommodations. AAS works with any student who requires academic accommodation regardless of program or course load.

Academic Accommodations (for students with disabilities) and Academic Consideration (for students faced with extenuating circumstances that can include short-term health issues) are governed by two different university policies. Learn more about Academic Accommodations versus Academic Consideration and how to access each.

Wellbeing Support

At Toronto Metropolitan University, we recognize that things can come up throughout the term that may interfere with a student’s ability to succeed in their coursework. These circumstances are outside of one’s control and can have a serious impact on physical and mental well-being. Seeking help can be a challenge, especially in those times of crisis.

If you are experiencing a mental health crisis, please call 911 and go to the nearest hospital emergency room. You can also access these outside resources at anytime:

If non-crisis support is needed, you can access these campus resources:

We encourage all Toronto Metropolitan University community members to access available resources to ensure support is reachable. You can find more resources available through the Toronto Metropolitan University Mental Health and Wellbeing website.