Online Course on
Generative AI – Principles and Applications
A structured online programme from IISc introduces the core principles of Generative AI and the technologies behind models that create text, images, and other content. It also highlights practical applications of generative AI across different domains.
Course at a Glance
Know the Course Instructor
Dr. Prathosh A P
He received his Ph.D. from the Indian Institute of Science (IISc), Bangalore in 2015 in the area of temporal data analysis, completing his dissertation just three years after his B.Tech in 2011, with several top-tier publications. He subsequently worked in corporate research labs such as Xerox Research India, Philips Research, and a California-based start-up, focusing on healthcare analytics, where he generated 15 U.S. patents, many of which are commercialized. In 2017, he joined IIT Delhi as an Assistant Professor in Electrical Engineering, teaching and researching machine learning and deep learning. He is currently a faculty member in the Department of Electrical Communication Engineering at IISc Bangalore. His research interests include deep representational learning, cross-domain generalization, and signal processing with applications in vision and speech. He is also co-founder of Cogniable.Tech, a healthcare AI start-up (winner of the Government of India AI Start-up Challenge), and actively collaborates with industry and medical institutions such as AIIMS. Beyond his technical work, he is deeply engaged with Sanskrit and Indian philosophical sciences, and often explores the intersections between AI and philosophy
Objectives of the Course
Provides an in-depth exploration of deep generative models, including their probabilistic foundations and learning algorithms.
Students will learn about various types of deep generative models such as variational autoencoders, generative adversarial networks, autoregressive models, Diffusion Models and Large Language Models and RLHF.
The course will cover both mathematical foundations and practical implementations of these models using popular frameworks like PyTorch.
Students will gain hands-on experience through lectures and assignments, allowing them to explore deep generative models across various Al tasks.
Course Syllabus
Introduction to Probabilistic Deep Generative Modelling, including Variational Divergence Minimization
Study of Generative Adversarial Networks (GANS, WGANs), Variational Autoencoders (VAES, VQVAE)
Understanding Denoising Diffusion Probabilistic Models (DDPMs)
Exploration of Conditional Diffusion, Score-based models and Large Language Models (LLMs)
Focus on sampling, quantization, and reinforcement learning-based alignment methods such as PPO and DPO
Who Can Apply & Who Can Benefit?
Who Can Apply?
- Basic Undergraduate degree
- Basic programming skills in Python
Who Can Benefit?
- Anyone interested in understanding the nuances of Generative AI from a mathematical perspective
Course Fee
Class Schedule
Reference Books
Ready to Enroll?
Apply online at iisc.online · New batches every semester (Jan–May and Aug–Dec)