Instructors: Prof. Lyle Muller | Prof. Marieke Mur
Emails: lmuller2@uwo.ca (Prof. Muller) | mmur@uwo.ca (Prof. Mur)

Course Dates: January 10th, 2023 - April 6th, 2023
Mid-Semester Break: February 20th - 24th, 2023
Lecture Times: Tuesdays & Thursdays 2:00 PM - 4:00 PM (ET)
Office Hours: TBA

Registration Fee: PSU Students - Free | Other Students - CAD$500

Prerequisites: 
This course is open to graduate students and senior undergraduates. There are no formal prerequisites for the course. However, you are expected to have a strong foundation in applied mathematics and programming.

We provide an online self-assessment that you can take prior to the start of the course to help you determine your level of background knowledge on the elementary topics listed above. If you do not have the background knowledge on these topics but are willing to learn, we can provide authorization to enroll in the course on a case-by-case basis. For those who would like to gain programming experience prior to the course, please consider taking a background course in scientific computing in the term before the course.

Evaluation: 
The overall course grade will be calculated as listed below:

• Assignments (8): 50%
• Midterm Project: 25%
• Final Project: 25%

The course will be graded according to problem sets, a midterm project, and a final project. Assignments need to be completed independently. The final project will be performed in small groups. The project involves implementing a model of a neural system and presenting the results in class.

Capacity Limit: 50 students

Format: Hybrid synchronous delivery

Course Description

This one-semester graduate course will provide you with an introduction to neural networks. You will learn the fundamentals of neural computation and explore how networks of neurons support brain information processing. You will be familiarized with mathematical approaches, computational science, and machine learning techniques. You will gain an in-depth knowledge of neural computations through weekly programming assignments.

Learning Outcomes

The course is designed to achieve three primary objectives:

1. You will have an intensive introduction to mathematical approaches to neural networks
2. You will learn to link neural computations to cognitive function
3. You will learn to model neural computations in a high-level language (Python)

Fundamental Topics

1. Mathematical models for neural and cognitive processes
2. Single-neuron models 
3. Dynamics of neural networks 
4. Random graph theory 
5. Simple models for memory 
6. Simple models for sensory processing 
7. Dimensionality reduction techniques 
8. Deep convolutional neural networks 
9. Recurrent neural networks 
10. Attractor network models

Course Materials

We will use the following textbooks: Theoretical Neuroscience by Dayan and Abbott and Deep Learning by Goodfellow, Bengio, and Courville. We will additionally assign recommended readings from primary literature when relevant for the coursework. We will also provide links to online resources for learning to program in Python. Readings and links will be posted on the course website. Students are responsible for checking the course website on a regular basis for news and updates.

Full Course Outline Here