Deep Learning Architecture and Algorithms

Description

This course provides an in-depth exploration of deep learning techniques and their applications in modern artificial intelligence systems, with a strong focus on the underlying algorithms that drive these models. Students will study neural network architectures, including feedforward networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and generative adversarial networks (GANs), examining the mathematical foundations and algorithmic strategies behind their design and training. The course covers essential topics such as gradient-based optimization methods, backpropagation, regularization techniques, and scalability of deep learning models. Emphasis is placed on practical implementation using deep learning libraries and frameworks, enabling students to build and deploy deep learning models for tasks in computer vision, natural language processing, and reinforcement learning. Ethical considerations and the limitations of deep learning are also discussed to foster responsible AI development. Prerequisite(s): SOFE 3620U