Neural Network Basics (Activation Functions) (2nd Offering)
Presenter: Ali Forooghi
Date: Friday, November 7th, 2025
Time: 12:00
Location: Workshop Space, 4th Floor - 300 Ouellette Ave., School of Computer Science, Advanced Computing Hub
Backpropagation, activation functions, and loss functions are the core pillars that enable neural networks to learn from data. This workshop provides an intuitive and practical exploration of how these components work together to form the foundation of deep learning. Participants will learn how activation functions introduce non-linearity, how loss functions quantify model performance, and how backpropagation uses gradients to optimize network weights. By the end of the workshop, attendees will be able to understand the mathematics driving their learning process.
- Introduction to Neural Networks and Learning Process
- Activation Functions
- Loss Functions
- Backpropagation
- Discussion and Q&A
- Basic understanding of Python programming
- Familiarity with fundamental ML concepts (No prior deep learning experience required)
Ali Forooghi, a Ph.D. student in the School of Computer Science at the University of Windsor with an interest in Natural Language Processing. (Email: foroogh@uwindsor.ca).