An Introduction to Variational Autoencoders — mentioned by p1esk

Wed, 29 Mar 2023 12:28:44 GMT

Basic autoencoders are conceptually easy, but try to understand how the VAE KL loss was derived. I remember I spent two days reading https://arxiv.org/abs/1906.02691 and I still didn't quite get it.

Paper and discussion history. A mention is not an endorsement.

An Introduction to Variational Autoencoders — mentioned by Dzugaru

Sat, 03 Sep 2022 09:29:51 GMT

It is fed using a fascinating mechanism called "cross-attention" that originated in the NN architecture called Transformer - which was used to achieve state-of-the-art translations. It uses something like associative memory, where a NN inside Stable Diffusion, that generates image (UNet, working in latent space), at almost each step "asks" the whole encoded prompt to provide data at various positions using query vector Q that is matched against key vectors K and value vectors V [0]. How Stable Diffusion works [1] as a whole is not really hard to comprehend at a high level - but you'll need…

Paper and discussion history. A mention is not an endorsement.

An Introduction to Variational Autoencoders · HackerPapers discussions

An Introduction to Variational Autoencoders — mentioned by p1esk

An Introduction to Variational Autoencoders — mentioned by Dzugaru