This course offers a comprehensive introduction to generative AI, covering its evolution from foundational AI techniques to modern advancements in deep learning. Students will explore key breakthroughs in neural networks that have enabled the development of cutting-edge generative models, including large language models (LLMs) such as ChatGPT, which are transforming fields like natural language processing, content generation, and AI-assisted coding. The course also delves into diffusion models, which are used for high-quality image generation and manipulation. Emphasizing both theoretical concepts and hands-on practice, students will learn core techniques such as model training, optimization, and debugging, while gaining practical experience in applying generative models to real-world problems. By the end of the course, students will have the knowledge and skills to develop, fine-tune, and implement generative AI models, preparing them to engage with the latest advancements in AI technology.

Deep learning has been revolutionizing the fields of object detection, classification, speech recognition, natural language processing, action recognition, scene understanding, and general pattern recognition. In some cases, results are on par with and even surpass the abilities of humans. Activity in this space is pervasive, ranging from academic institutions to small startups to large corporations. This course emphasizes convolutional neural networks (CNNs) and recurrent neural networks (RNNs), but additionally covers reinforcement learning and generative adversarial networks. In addition to achieving a comprehensive theoretical understanding, students will understand current state-of-the-art methods, and get hands-on experience at training custom models using popular deep learning frameworks.

Graduate level topics and subject areas that are not among the courses typically offered are provided under the title of Special Topics. Such courses are offered in a normal format; that is, regularly scheduled class sessions with an instructor.

Doctoral-level research by the candidate on an appropriate topic as arranged between the candidate and the research advisor.

Continuation of Thesis