Academic Calendar - 2024
Western University Academic Calendar. - 2024
Artificial Intelligence Systems Engineering
Artificial Intelligence Systems Engineering 2205A/B ALGORITHMS & DATA STRUCTURES FOR OBJECT-ORIENTED DESIGN
Survey of important computer algorithms and related data structures used in object-oriented software engineering. Design, performance analysis and implementation of such algorithms, stressing their practical use and performance certification of large software applications. Understand how to "seal" designs to guarantee performance goals and to ensure that error conditions are caught.
Antirequisite(s): Computer Science 2210A/B, Software Engineering 2205A/B.
Extra information: 3 lecture hours, 2 laboratory hours. Restricted to students enrolled in the Artificial Intelligence Systems Engineering program.
Prerequisite(s): Computer Science 1026A/B or Engineering Science 1036A/B.
Course Weight: 0.50
Return to top
AISE 2251A/B is a group project course illustrating the design and implementation of software engineering design concepts. It covers integration with third-party applications and big data sources. Real-time and distributed systems, and architectural design will be briefly covered.
Antirequisite(s): Computer Science 2212A/B/Y, Software Engineering 2203A/B, the former Software Engineering 2251A/B.
Prerequisite(s): AISE 2205A/B (or Software Engineering 2205A/B if taken prior to 2024-25), Engineering Science 1036A/B or Computer Science 1026A/B.
Extra Information: 3 lecture hours, 3 laboratory hours.
Course Weight: 0.50
Return to top
The course covers: 1) Introduction to data pipelines, distributed data management, and streamline data processing; 2) Data manipulation and data structure for big data; and 3) Design and implementation of an engineering group project illustrating the machine learning and data engineering concepts being taught.
Prerequisite(s): AISE 2205A/B (or SE 2205A/B if taken prior to 2024-25), AISE 2251A/B (or the former SE 2251A/B), AISE 3309A/B (or SE 3309A/B if taken prior to 2024-25), Data Science 3000A/B.
Extra Information: 3 lecture hours/week, 2 lab hour/week.
Course Weight: 0.50
Return to top
This course explores the fundamental issues of fairness and bias in machine learning. In addition, the course explores many aspects of building ethical models while considering human bias and dataset awareness. Furthermore, the course will explore fundamental concepts involved in privacy and security of machine learning projects. Topics such as how to protect users from privacy violations while building useful transparent predictive models will be explored.
Prerequisite(s): Data Science 3000A/B.
Extra Information: 3 lecture hours/week, 2 lab hour/week.
Course Weight: 0.50
Return to top
The focus is to teach database fundamentals required in the development and evolution of most software applications by providing a basic introduction to the principles of relational database management systems such as Entity-Relationship approach to data modeling, relational model of database management systems and the use of query languages.
Antirequisite(s): Computer Science 3319A/B, Computer Science 3120A/B, Software Engineering 3309A/B.
Extra information: 3 lecture hours, 2 laboratory hours. Restricted to students enrolled in the Artificial Intelligence Systems Engineering program.
Prerequisite(s): AISE 2205A/B (or Software Engineering 2205A/B if taken prior to 2024-25), AISE 2251A/B (or the former Software Engineering 2251A/B).
Course Weight: 0.50
Return to top
This course covers: 1) Architecture of Cyber-Physical world. 2) Modelling of systems in continuous-time. Transfer functions. Stability. Feedback, and 3) Interface between physical and cyber worlds, including sensor, actuators, and sampling. Coordinate Transform, A/D and D/A conversion (electronics) and principles of data collection. Notion of information and control.
Antirequisite(s): the former ECE 3350A/B.
Prerequisite(s): Numerical and Mathematic Methods 2270A/B, Numerical and Mathematical Methods 2276A/B or Numerical and Mathematical Methods 2277A/B, Physics 1302A/B or Physics 1402A/B.
Extra Information: 3 lecture hours, 2 laboratory hours.
Course Weight: 0.50
Return to top
Sampling and reconstruction of signals, discrete signals and systems, difference equations and state-space models of digital systems, z-transform and system functions, finite impulse response (FIR) and infinite impulse response (IIR) systems, their mathematical description and frequency response, Fast Fourier transform, filter structures, basics of spectral analysis, data collection.
Antirequisite(s): ECE 3331A/B, the former ECE 3351A/B.
Prerequisite(s): AISE 3350A/B or the former ECE 3350A/B if taken prior to 2024-25.
Extra Information: 3 lecture hours, 2 laboratory hours.
Course Weight: 0.50
Return to top
This course introduces deep learning models for time series data. In this course, the students will become familiar with sequence models and their engineering applications. The students are introduced to Recurrent Neural Networks (RNNs) and commonly - used variants such as Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTMs). In addition, the course introduces transformer architectures and their engineering applications. Students will get hands- on experience with Deep Learning from a series of practical engineering case-studies.
Prerequisite(s): Data Science 3000A/B, AISE 3010A/B.
Extra Information: 3 lecture hours/week, 2 lab hour/week.
Course Weight: 0.50
Return to top
Artificial Intelligence Systems Engineering 4020A/B ARTIFICIAL INTELLIGENCE SYSTEMS ENGINEERING DESIGN I
A large engineering project in the field of main engineering degree illustrating the machine learning and data engineering concepts through design and implementation. The course promotes team interaction in a professional setting.
Prerequisite(s): Data Science 3000A/B, AISE 3010A/B.
Extra Information: 1 lecture hour/week, 3 lab hours/week.
Course Weight: 0.50
Return to top
Artificial Intelligence Systems Engineering 4050 ARTIFICIAL INTELLIGENCE SYSTEMS ENGINEERING DESIGN II
Second large engineering project in the field of main engineering degree illustrating the machine learning and data engineering concepts through design and implementation. The course promotes team interaction in a professional setting. Individual students or project groups are carried out under the supervision of a faculty member. Progress reports and a final engineering report are prepared; each student must deliver a public lecture on the work performed.
Prerequisite(s): Completion of fourth year of the Artificial Intelligence Systems Engineering program.
Extra Information: 6 lab hours/week, both terms.
Course Weight: 1.00
Return to top
Artificial Intelligence Systems Engineering 4430A/B INTRODUCTION TO COMPUTER NETWORKING, SECURITY & IOT SYSTEMS
Principles of computer networking architecture/layers and protocols, IoT network systems, protocols, security, and connections to cloud services with an emphasis on the ability to interface and collect data from things and move them securely through the internet to process in public and private data centers.
Antirequisite(s): Computer Science 3357A/B, ECE 4436A/B, the former SE 4430A/B.
Prerequisite(s): AISE 2205A/B (or SE 2205A/B if taken prior to 2024-25), Engineering Science 1036A/B.
Extra Information: 3 lecture hours, 3 laboratory hours.
Course Weight: 0.50
Return to top
The course covers: 1) State-space control of systems using data processing algorithms. Adaptive algorithms. Implementation of Kalman filtering; 2) Use of ML in control of real-world Physical systems and Cyber systems.
Antirequisite(s): the former ECE 4450A/B.
Extra Information: 3 lecture hours, 2 laboratory hours.
Course Weight: 0.50
Return to top
Artificial Intelligence Systems Engineering
Artificial Intelligence Systems Engineering 2205A/B ALGORITHMS & DATA STRUCTURES FOR OBJECT-ORIENTED DESIGN
Survey of important computer algorithms and related data structures used in object-oriented software engineering. Design, performance analysis and implementation of such algorithms, stressing their practical use and performance certification of large software applications. Understand how to "seal" designs to guarantee performance goals and to ensure that error conditions are caught.
Antirequisite(s): Computer Science 2210A/B, Software Engineering 2205A/B.
Extra information: 3 lecture hours, 2 laboratory hours. Restricted to students enrolled in the Artificial Intelligence Systems Engineering program.
Prerequisite(s): Computer Science 1026A/B or Engineering Science 1036A/B.
Course Weight: 0.50
Return to top
AISE 2251A/B is a group project course illustrating the design and implementation of software engineering design concepts. It covers integration with third-party applications and big data sources. Real-time and distributed systems, and architectural design will be briefly covered.
Antirequisite(s): Computer Science 2212A/B/Y, Software Engineering 2203A/B, the former Software Engineering 2251A/B.
Prerequisite(s): AISE 2205A/B (or Software Engineering 2205A/B if taken prior to 2024-25), Engineering Science 1036A/B or Computer Science 1026A/B.
Extra Information: 3 lecture hours, 3 laboratory hours.
Course Weight: 0.50
Return to top
The course covers: 1) Introduction to data pipelines, distributed data management, and streamline data processing; 2) Data manipulation and data structure for big data; and 3) Design and implementation of an engineering group project illustrating the machine learning and data engineering concepts being taught.
Prerequisite(s): AISE 2205A/B (or SE 2205A/B if taken prior to 2024-25), AISE 2251A/B (or the former SE 2251A/B), AISE 3309A/B (or SE 3309A/B if taken prior to 2024-25), Data Science 3000A/B.
Extra Information: 3 lecture hours/week, 2 lab hour/week.
Course Weight: 0.50
Return to top
This course explores the fundamental issues of fairness and bias in machine learning. In addition, the course explores many aspects of building ethical models while considering human bias and dataset awareness. Furthermore, the course will explore fundamental concepts involved in privacy and security of machine learning projects. Topics such as how to protect users from privacy violations while building useful transparent predictive models will be explored.
Prerequisite(s): Data Science 3000A/B.
Extra Information: 3 lecture hours/week, 2 lab hour/week.
Course Weight: 0.50
Return to top
The focus is to teach database fundamentals required in the development and evolution of most software applications by providing a basic introduction to the principles of relational database management systems such as Entity-Relationship approach to data modeling, relational model of database management systems and the use of query languages.
Antirequisite(s): Computer Science 3319A/B, Computer Science 3120A/B, Software Engineering 3309A/B.
Extra information: 3 lecture hours, 2 laboratory hours. Restricted to students enrolled in the Artificial Intelligence Systems Engineering program.
Prerequisite(s): AISE 2205A/B (or Software Engineering 2205A/B if taken prior to 2024-25), AISE 2251A/B (or the former Software Engineering 2251A/B).
Course Weight: 0.50
Return to top
This course covers: 1) Architecture of Cyber-Physical world. 2) Modelling of systems in continuous-time. Transfer functions. Stability. Feedback, and 3) Interface between physical and cyber worlds, including sensor, actuators, and sampling. Coordinate Transform, A/D and D/A conversion (electronics) and principles of data collection. Notion of information and control.
Antirequisite(s): the former ECE 3350A/B.
Prerequisite(s): Numerical and Mathematic Methods 2270A/B, Numerical and Mathematical Methods 2276A/B or Numerical and Mathematical Methods 2277A/B, Physics 1302A/B or Physics 1402A/B.
Extra Information: 3 lecture hours, 2 laboratory hours.
Course Weight: 0.50
Return to top
Sampling and reconstruction of signals, discrete signals and systems, difference equations and state-space models of digital systems, z-transform and system functions, finite impulse response (FIR) and infinite impulse response (IIR) systems, their mathematical description and frequency response, Fast Fourier transform, filter structures, basics of spectral analysis, data collection.
Antirequisite(s): ECE 3331A/B, the former ECE 3351A/B.
Prerequisite(s): AISE 3350A/B or the former ECE 3350A/B if taken prior to 2024-25.
Extra Information: 3 lecture hours, 2 laboratory hours.
Course Weight: 0.50
Return to top
This course introduces deep learning models for time series data. In this course, the students will become familiar with sequence models and their engineering applications. The students are introduced to Recurrent Neural Networks (RNNs) and commonly - used variants such as Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTMs). In addition, the course introduces transformer architectures and their engineering applications. Students will get hands- on experience with Deep Learning from a series of practical engineering case-studies.
Prerequisite(s): Data Science 3000A/B, AISE 3010A/B.
Extra Information: 3 lecture hours/week, 2 lab hour/week.
Course Weight: 0.50
Return to top
Artificial Intelligence Systems Engineering 4020A/B ARTIFICIAL INTELLIGENCE SYSTEMS ENGINEERING DESIGN I
A large engineering project in the field of main engineering degree illustrating the machine learning and data engineering concepts through design and implementation. The course promotes team interaction in a professional setting.
Prerequisite(s): Data Science 3000A/B, AISE 3010A/B.
Extra Information: 1 lecture hour/week, 3 lab hours/week.
Course Weight: 0.50
Return to top
Artificial Intelligence Systems Engineering 4050 ARTIFICIAL INTELLIGENCE SYSTEMS ENGINEERING DESIGN II
Second large engineering project in the field of main engineering degree illustrating the machine learning and data engineering concepts through design and implementation. The course promotes team interaction in a professional setting. Individual students or project groups are carried out under the supervision of a faculty member. Progress reports and a final engineering report are prepared; each student must deliver a public lecture on the work performed.
Prerequisite(s): Completion of fourth year of the Artificial Intelligence Systems Engineering program.
Extra Information: 6 lab hours/week, both terms.
Course Weight: 1.00
Return to top
Artificial Intelligence Systems Engineering 4430A/B INTRODUCTION TO COMPUTER NETWORKING, SECURITY & IOT SYSTEMS
Principles of computer networking architecture/layers and protocols, IoT network systems, protocols, security, and connections to cloud services with an emphasis on the ability to interface and collect data from things and move them securely through the internet to process in public and private data centers.
Antirequisite(s): Computer Science 3357A/B, ECE 4436A/B, the former SE 4430A/B.
Prerequisite(s): AISE 2205A/B (or SE 2205A/B if taken prior to 2024-25), Engineering Science 1036A/B.
Extra Information: 3 lecture hours, 3 laboratory hours.
Course Weight: 0.50
Return to top
The course covers: 1) State-space control of systems using data processing algorithms. Adaptive algorithms. Implementation of Kalman filtering; 2) Use of ML in control of real-world Physical systems and Cyber systems.
Antirequisite(s): the former ECE 4450A/B.
Extra Information: 3 lecture hours, 2 laboratory hours.