AIML 3310 - Introduction to Deep Learning

Prerequisites: AIML 2220, AIML 2211, and INSE 3320. The goal of this course is to provide a foundational introduction to deep learning systems and their implementation using libraries such as tensorflow and pytorch. The course covers the core principles of representation learning, neural networks architectures, loss functions, optimization, initialization, performance metrics, and regularization, as well as how these ideas translate into real-world applications. Through hands-on programming exercises and guided projects, students will implement and experiment with key architectures such as shallow networks, convolutional neural networks, residual networks, generative adversarial networks and transformers. By the end of the course, students will be equipped with both the conceptual understanding and practical skills needed to build, train, and evaluate deep learning models across a variety of domains and data types including vision and language. 3 credits.