arXiv:1906.02691cs.LG
Variational autoencoders provide a principled framework for learning deep latent-variable models and corresponding inference models. In this work, we provide an introduction to variational autoencoders and some important extensions.
Linked by 2 identifiable commenters in 2 comments across 2 threads, from Sep 2022 to Mar 2023.
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…
Connected through shared HN threads, not inferred similarity or a recommendation.
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.
p1eskView on HNParent context