Program Requirements
The Master of Engineering in Electrical Engineering; Non-Thesis - Applied Artificial Intelligence is a professional program of 45 credits. The program provides the foundation for applications of Artificial Intelligence (AI) techniques and experience building an AI system in various fields of interest. The program may be completed on a part-time basis.
Required Courses (14 credits)
-
ECSE 551 Machine Learning for Engineers (4 credits)
Overview
Electrical Engineering : Introduction to machine learning: challenges and fundamental concepts. Supervised learning: Regression and Classification. Unsupervised learning. Curse of dimensionality: dimension reduction and feature selection. Error estimation and empirical validation. Emphasis on good methods and practices for deployment of real systems.
Terms: Fall 2024, Winter 2025
Instructors: Armanfard, Narges (Fall) Armanfard, Narges (Winter)
-
ECSE 552 Deep Learning (4 credits)
Overview
Electrical Engineering : Overview of mathematical background and basics of machine learning, deep feedforward networks, regularization for deep learning, optimization for training deep learning models, convolutional neural networks, recurrent and recursive neural networks, practical considerations,applications of deep learning, recent models and architectures in deep learning.
Terms: Winter 2025
Instructors: Emad, Amin (Winter)
-
ECSE 679D1 Project in Applied Artificial Intelligence (3 credits)
Overview
Electrical Engineering : A project on a topic related to an application of Artificial Intelligence.
Terms: This course is not scheduled for the 2024-2025 academic year.
Instructors: There are no professors associated with this course for the 2024-2025 academic year.
Prerequisites: ECSE 551
Restrictions: Open only to students in the M.Eng. in Electrical Engineering; Non-Thesis - Applied Artificial Intelligence program
No credit will be given for this course unless both ECSE 679D1 and ECSE 679D2 are successfully completed in consecutive terms
-
ECSE 679D2 Project in Applied Artificial Intelligence (3 credits)
Overview
Electrical Engineering : See ECSE 679D1 for course description.
Terms: This course is not scheduled for the 2024-2025 academic year.
Instructors: There are no professors associated with this course for the 2024-2025 academic year.
No credit will be given for this course unless both ECSE 679D1 and ECSE 679D2 are successfully completed in consecutive terms
Restrictions: Open only to students in the M.Eng. in Electrical Engineering; Non-Thesis - Applied Artificial Intelligence program.
Prerequisites: ECSE 551
Complementary Courses
(18-24 credits)
Group A: Artificial Intelligence Focused
6-8 credits from the following:
-
ECSE 526 Artificial Intelligence (3 credits)
Overview
Electrical Engineering : Design principles of autonomous agents, agent architectures, machine learning, neural networks, genetic algorithms, and multi-agent collaboration. The course includes a term project that consists of designing and implementing software agents that collaborate and compete in a simulated environment.
Terms: Fall 2024
Instructors: Cooperstock, Jeremy (Fall)
-
ECSE 555 Advanced Topics in Artificial Intelligence (4 credits)
Overview
Electrical Engineering : Selected topics in areas of artificial intelligence that are of current research interest.
Terms: Winter 2025
Instructors: There are no professors associated with this course for the 2024-2025 academic year.
3-0-9
Restriction: Permission of instructor
-
ECSE 556 Machine Learning in Network Biology (4 credits)
Overview
Electrical Engineering : Basics of machine learning; basics of molecular biology; network-guided machine learning in systems biology; network-guided bioinformatics analysis; analysis of biological networks; network module identification; global and local network alignment; construction of biological networks.
Terms: Fall 2024
Instructors: Emad, Amin (Fall)
3-0-9
Restrictions: Permission of Instructor.
-
ECSE 557 Introduction to Ethics of Intelligent Systems (3 credits)
Overview
Electrical Engineering : Ethics and social issues related to AI and robotic systems. Consideration for normative values (e.g., fairness) in the design. Ethics principles, data and privacy issues, ethics challenges in interaction and interface design.
Terms: Fall 2024
Instructors: Moon, AJung (Fall)
-
ECSE 626 Statistical Computer Vision (4 credits)
Overview
Electrical Engineering : An overview of statistical and machine learning techniques as applied to computer vision problems, including: stereo vision, motion estimation, object and face recognition, image registration and segmentation. Topics include regularization, probabilistic inference, information theory, Gaussian Mixture Models, Markov-Chain Monte Carlo methods, importance sampling, Markov random fields, principal and independent components analysis, probabilistic deep learning methods including variational models, Bayesian deep learning.
Terms: Fall 2024
Instructors: Arbel, Tal (Fall)
-
ECSE 683 Topics in Vision and Robotics (4 credits)
Overview
Electrical Engineering : Special topics in vision and robotics.
Terms: Winter 2025
Instructors: Lin, Hsiu-Chin (Winter)
(3-0-9)
Group B: Mathematical Foundations of Artificial Intelligence
3-4 credits from the following:
-
COMP 540 Matrix Computations (4 credits)
Overview
Computer Science (Sci) : Designing and programming reliable numerical algorithms. Stability of algorithms and condition of problems. Reliable and efficient algorithms for solution of equations, linear least squares problems, the singular value decomposition, the eigenproblem and related problems. Perturbation analysis of problems. Algorithms for structured matrices.
Terms: Winter 2025
Instructors: Chang, Xiao-Wen (Winter)
-
ECSE 500 Mathematical Foundations of Systems (3 credits)
Overview
Electrical Engineering : Basic set theories and algebraic structures, linear spaces, linear mappings, topological and metric spaces, separable spaces, continuity, compactness, Lebesque measure on Euclidean spaces, measurability, Banach spaces, Hilbert spaces, linear bounded operators in Banach spaces, dual spaces, adjoint operators, the Orthogonal Projection Theorem, properties of the Fourier series, convergence in probability.
Terms: Fall 2024
Instructors: C么t茅, Fran莽ois (Fall)
(3-0-6)
Restriction: Open only to graduate students within the Faculty of Engineering.
-
ECSE 501 Linear Systems (3 credits)
Overview
Electrical Engineering : Mathematical models of linear systems, fundamental solution and transition matrices, non-homogeneous linear equations, controllability and observability of linear systems, reachable subspaces, Cayley-Hamilton's Theorem, Kalman's controllability and observability rank conditions, minimal realizations, frequency response, invariant subspaces, finite and infinite horizon linear regulator problems, uniform, exponential, and input-output stability, the Lyapunov equation.
Terms: Fall 2024
Instructors: Caines, Peter Edwin (Fall)
(3-0-6)
Corequisite: ECSE 500 or permission of instructor
-
ECSE 507 Optimization and Optimal Control (3 credits)
Overview
Electrical Engineering : General introduction to optimization methods including steepest descent, conjugate gradient, Newton algorithms. Generalized matrix inverses and the least squared error problem. Introduction to constrained optimality; convexity and duality; interior point methods. Introduction to dynamic optimization; existence theory, relaxed controls, the Pontryagin Maximum Principle. Sufficiency of the Maximum Principle.
Terms: Winter 2025
Instructors: Radhakrishnan, Sindhu (Winter)
-
ECSE 509 Probability and Random
Signals 2 (3 credits)
Overview
Electrical Engineering : Multivariate Gaussian distributions; finite-dimensional mean-square estimation (multivariate case); principal components; introduction to random processes; weak stationarity: correlation functions, spectra, linear processing and estimation; Poisson processes and Markov chains: state processes, invariant distributions; stochastic simulation.
Terms: Fall 2024
Instructors: Mahajan, Aditya (Fall)
-
ECSE 543 Numerical Methods in Electrical Engineering (3 credits)
Overview
Electrical Engineering : DC resistor networks and sparse matrix methods. Nonlinear electric and magnetic circuits: curve-fitting; the Newton-Raphson method. Finite elements for electrostatics. Transient analysis of circuits: systems of Ordinary differential equations; stiff equations. Transient analysis of induced currents. Solution of algebraic eigenvalue problems. Scattering of electromagnetic waves: the boundary element method; numerical integration.
Terms: Fall 2024
Instructors: Giannacopoulos, Dennis (Fall)
-
ECSE 621 Statistic Detection and Estimation (4 credits)
Overview
Electrical Engineering : Statistical detection and estimation lies at the intersection of telecommunications, signal processing and mathematical statistics. Subjects include: hypothesis testing (Neyman-Pearson, Bayes, minimax, nuisance parameters, composite hypotheses, generalized likelihood), estimation theory (maximum-likelihood, maximum aposteriory probability, linear estimation, Cramer-Rao bounds).
Terms: This course is not scheduled for the 2024-2025 academic year.
Instructors: There are no professors associated with this course for the 2024-2025 academic year.
Group C: Applications of Artificial Intelligence
9-12 credits from the following:
-
COMP 545 Natural Language Understanding with Deep Learning
(4 credits)
Overview
Computer Science (Sci) : Neural network-based methods for natural language understanding (NLU) and computational semantics. Continuous representations for words, phrases, sentences, and discourse, and their connection to formal semantics. Practical and ethical considerations in applications such as text classification, question answering, and conversational assistants.
Terms: This course is not scheduled for the 2024-2025 academic year.
Instructors: There are no professors associated with this course for the 2024-2025 academic year.
-
COMP 549 Brain-Inspired Artificial Intelligence (3 credits)
Overview
Computer Science (Sci) : Overview of the influence of neuroscience and psychology on Artificial Intelligence (AI). Historical topics: perceptrons, the PDP framework, Hopfield nets, Boltzmann and Helmholtz machines, and the behaviourist origins of reinforcement learning. Modern topics: deep learning, attention, memory and consciousness. Emphasis on understanding the interdisciplinary foundations of modern AI.
Terms: Winter 2025
Instructors: Richards, Blake (Winter)
-
COMP 558 Fundamentals of Computer Vision (4 credits)
Overview
Computer Science (Sci) : Image filtering, edge detection, image features and histograms, image segmentation, image motion and tracking, projective geometry, camera calibration, homographies, epipolar geometry and stereo, point clouds and 3D registration. Applications in computer graphics and robotics.
Terms: Fall 2024
Instructors: Siddiqi, Kaleem (Fall)
-
COMP 565 Machine Learning in Genomics and Healthcare (4 credits)
Overview
Computer Science (Sci) : Linear models in statistical genetics, causal inference, single-cell genomics, multi-omic learning, electronic health record mining. Applications of machine learning techniques: linear regression, latent factor models, variational Bayesian inference, neural networks, model interpretation.
Terms: Fall 2024
Instructors: Li, Yue (Fall)
-
COMP 579 Reinforcement Learning (4 credits)
Overview
Computer Science (Sci) : Bandit algorithms, finite Markov decision processes, dynamic programming, Monte-Carlo Methods, temporal-difference learning, bootstrapping, planning, approximation methods, on versus off policy learning, policy gradient methods temporal abstraction and inverse reinforcement learning.
Terms: Winter 2025
Instructors: Precup, Doina; Pr茅mont-Schwarz, Isabeau (Winter)
-
COMP 585 Intelligent Software
Systems
(4 credits)
Overview
Computer Science (Sci) : Practical aspects of building software systems with machine learning components: requirements, design, delivery, quality assessment, and collaboration. Consideration of a user-centered mindset in development; integration of design and development considerations relevant to artificial intelligence, such as security, privacy, and fairness.
Terms: This course is not scheduled for the 2024-2025 academic year.
Instructors: There are no professors associated with this course for the 2024-2025 academic year.
-
COMP 588 Probabilistic Graphical Models (4 credits)
Overview
Computer Science (Sci) : Representation, inference and learning with graphical models; directed and undirected graphical models; exact inference; approximate inference using deterministic optimization based methods, stochastic sampling based methods; learning with complete and partial observations.
Terms: Winter 2025
Instructors: Ravanbakhsh, Siamak (Winter)
-
COMP 685 Machine Learning Applied to
Climate Change (4 credits)
Overview
Computer Science (Sci) : Applications of machine learning in fighting climate change, including use cases in electricity systems, buildings, transportation, agriculture and other land use, disaster response, and other areas. Review of recent research literature, with emphasis on when machine learning is relevant and helpful, and how to go about scoping, developing, and deploying a project so that it has the intended impact.
Terms: Fall 2024
Instructors: Rolnick, David (Fall)
1. This course is aimed at graduate students with at least some prior experience in machine learning and ability to read and assimilate research literature across many areas of machine learning. Prior experience with climate change-related topics is not required, but willingness to learn about these topics is.
-
ECSE 506 Stochastic Control and Decision Theory (3 credits)
Overview
Electrical Engineering : Modelling of stochastic control systems, controlled Markov processes, dynamic programming, imperfect and delayed observations, linear quadratic and Gaussian (LQG) systems, team theory, information structures, static and dynamic teams, dynamic programming for teams,multi-armed bandits.
Terms: This course is not scheduled for the 2024-2025 academic year.
Instructors: There are no professors associated with this course for the 2024-2025 academic year.
(3-0-6)
Prerequisites: ECSE 509
-
ECSE 508 Multi-Agent Systems (3 credits)
Overview
Electrical Engineering : Introduction to game theory, strategic games, extensive form games with perfect and imperfect information, repeated games and folk theorems, cooperative game theory, introduction to mechanism design, markets and market equilibrium, pricing and resource allocation, application in telecommunication networks, applications in communication networks, stochastic games.
Terms: Winter 2025
Instructors: Mahajan, Aditya (Winter)
(3-0-6)
Prerequisite(s): ECSE 205 or equivalent.
-
ECSE 541 Design of Multiprocessor Systems-颅on-颅Chip (3 credits)
Overview
Electrical Engineering : Modelling, design, evaluation, and optimization of multiprocessor systems-on-chips (MPSoCs). Introduction to system-level modelling of MPSoC architecture; system performance, power, and lifetime modelling; fault and defect tolerance; automatic general and heuristic design space exploration and design optimization; resource allocation, application mapping, and task scheduling.
Terms: This course is not scheduled for the 2024-2025 academic year.
Instructors: There are no professors associated with this course for the 2024-2025 academic year.
-
ECSE 544 Computational Photography (4 credits)
Overview
Electrical Engineering : An overview of techniques and theory underlying computational photography. Topics include: radiometry and photometry; lenses and image formation; electronic image sensing; colour processing; lightfield cameras; image deblurring; super-resolution methods; image denoising; flash photography; image matting and compositing; high dynamic range imaging and tone mapping; image retargeting; image stitching.
Terms: Winter 2025
Instructors: Clark, James J (Winter)
-
ECSE 546 Advanced Image Synthesis (4 credits)
Overview
Electrical Engineering : Introduction to mathematical models of light transport and the numerical techniques used to generate realistic images in computer graphics. Offline (i.e., raytracing) and interactive (i.e., shader-based) techniques. Group project addressing important applied research problems.
Terms: Fall 2024
Instructors: Nowrouzezahrai, Derek (Fall)
(3-2-7)
Restrictions: For graduate students in Electrical and Computer Engineering and undergraduate Honours Electrical Engineering students.
Not open to students who have taken or are taking ECSE 446.
-
ECSE 554 Applied Robotics
(4 credits)
Overview
Electrical Engineering : The approach and the challenges in the key components of manipulators and locomotors: representations, kinematics, dynamics, rigid-body chains, redundant systems, underactuated systems, control, planning, and perception. Practical aspects of robotics: collisions, integrating sensory feedback, and development of real-time software.
Terms: Fall 2024
Instructors: Lin, Hsiu-Chin (Fall)
-
MECH 559 Engineering Systems Optimization (3 credits)
Overview
Mechanical Engineering : Introduction to systems-oriented engineering design optimization. Emphasis on i) understanding and representing engineering systems and their structure, ii) obtaining, developing, and managing adequate computational (physics- and data-based) models for their analysis, iii) constructing appropriate design models for their synthesis, and iv) applying suitable algorithms for their numerical optimization while accounting for systems integration issues. Advanced topics such as coordination of distributed problems and non-deterministic design optimization methods.
Terms: Fall 2024
Instructors: Kokkolaras, Michael (Fall)
Elective Courses
(7-13 credits)
7-13 credits at the 500 or 600 level (excluding ECSE 691 to ESCE 697)
* No more than 16 credits in total may be outside the Department. With the exception of courses in the Complementary Courses list, non-departmental courses require Departmental Approval. In exceptional circumstances and with proper justification, students may be permitted to take more than 16 credits of non-Departmental courses; approval from the Graduate Program Director or delegate is required.
