This course provides an in-depth exploration of deep learning techniques, building on a foundational understanding of neural networks. It begins with a review of basic architectures before advancing to convolutional neural networks (CNNs), recurrent neural networks (RNNs), encoder-decoder structures, and sequence-to-sequence models. The course delves into the transformer architecture, which underpins state-of-the-art models like GPT. Students will gain experience with natural language processing (NLP), large language models, understand how GPT functions, and explore the emerging field of prompt engineering. The course also introduces agentic frameworks that support autonomous decision-making in AI systems. Prerequisite: INSY 5339.