Gaussian Mixture Variational Autoencoder

Introduced by Aguilera et al. in Regularizing Transformers With Deep Probabilistic Layers

GMVAE, or Gaussian Mixture Variational Autoencoder, is a stochastic regularization layer for transformers. A GMVAE layer is trained using a 700-dimensional internal representation of the first MLP layer. For every output from the first MLP layer, the GMVAE layer first computes a latent low-dimensional representation sampling from the GMVAE posterior distribution to then provide at the output a reconstruction sampled from a generative model.

Source: Regularizing Transformers With Deep Probabilistic Layers

Read Paper

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Dimensionality Reduction	1	33.33%
Protein Folding	1	33.33%
Decoder	1	33.33%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Regularization