DESCRIPTION
Generative AI methods that can be used to create synthetic text, images or videos. Large Language Models, such as ChatGPT can be used to create smoot text. The fueled the recent wave of AI revolution. Generative Adversarial Networks (GANs) and Diffusion Models are very efficient in creating synthetic images or videos. They can be used in a wide range of applications namely, unconditional image generation, image super-resolution, inpainting, repainting, or restoration.
Figure 1: LLM evolutionary tree.
Figure 2: Diffusion Model Process.
LECTURE LIST
CVML WEB LECTURE MODULE SCHEDULE
This module has been designed to be mastered within 1 month (or less), if you have proper background (at least early undergraduate student in an EE, ECE, CS, CSE or any Engineering or Exact Sciences Department).
We propose that you follow the above mentioned Lecture order. You may want to skip few Lectures that might not be of immediate interest to you for later study.
On average you can study 4 lectures per week. The related effort is as follows:
Lecture pdf study and filling the related understanding questionnaire: 1-2 hours per lecture (on average, depending on your background).