Topographic VAEs Learn Equivariant Capsules - Machine Learning Research Paper Explained
Offered By: Yannic Kilcher via YouTube
Course Description
Overview
Explore a detailed explanation of the research paper on Topographic Variational Autoencoders (TVAEs) and their ability to learn equivariant capsules in this comprehensive video. Delve into the architecture overview, compare TVAEs to regular VAEs, and understand the generative mechanism formulation. Examine the non-Gaussian latent space, topographic product of Student-t distributions, and the introduction of temporal coherence. Learn about the Topographic VAE model, analyze experimental results, and gain insights from the conclusion and comments. Discover how TVAEs bridge the concepts of topographic organization and equivariance in neural networks, potentially advancing deep generative models and unsupervised learning of equivariant features.
Syllabus
- Intro
- Architecture Overview
- Comparison to regular VAEs
- Generative Mechanism Formulation
- Non-Gaussian Latent Space
- Topographic Product of Student-t
- Introducing Temporal Coherence
- Topographic VAE
- Experimental Results
- Conclusion & Comments
Taught by
Yannic Kilcher
Related Courses
Machine Learning with Graphs - Fall 2019Stanford University via YouTube Generative Models With Domain Knowledge for Weakly Supervised Clustering
Stanford University via YouTube Deep Generative Models and Stable Diffusion: Revolution in Visual Synthesis - Lecture by Björn Ommer
Lennart Svensson via YouTube Toward Brain Computer Interface - Deep Generative Models for Brain Reading
MITCBMM via YouTube Deep Generative Models for Speech and Images
MITCBMM via YouTube