YoVDO

Diffusion Models Beat GANs on Image Synthesis - Machine Learning Research Paper Explained

Offered By: Yannic Kilcher via YouTube

Tags

Generative Adversarial Networks (GAN) Courses Machine Learning Courses Image Synthesis Courses Probabilistic Models Courses Generative Models Courses Diffusion Models Courses

Course Description

Overview

Explore a comprehensive analysis of the research paper "DDPM - Diffusion Models Beat GANs on Image Synthesis" in this 55-minute video lecture. Delve into the world of Denoising Diffusion Probabilistic Models (DDPMs) and discover how they outperform GANs in image generation tasks. Learn about the formal probabilistic foundation of DDPMs, their training process, and various improvements such as noise schedule optimization and classifier guidance. Examine the experimental results that demonstrate DDPMs' superior performance on ImageNet datasets at different resolutions. Gain insights into the potential future of image synthesis techniques and the implications for the field of machine learning.

Syllabus

- Intro & Overview
- Denoising Diffusion Probabilistic Models
- Formal derivation of the training loss
- Training in practice
- Learning the covariance
- Improving the noise schedule
- Reducing the loss gradient noise
- Classifier guidance
- Experimental Results


Taught by

Yannic Kilcher

Related Courses

Diffusion Models Beat GANs on Image Synthesis - ML Coding Series - Part 2
Aleksa Gordić - The AI Epiphany via YouTube
OpenAI GLIDE - Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Aleksa Gordić - The AI Epiphany via YouTube
Food for Diffusion
HuggingFace via YouTube
Imagen: Text-to-Image Generation Using Diffusion Models - Lecture 9
University of Central Florida via YouTube
Denoising Diffusion-Based Generative Modeling
Open Data Science via YouTube