Generative Models

AutoEncoder

Introduced by Hinton et al. in Reducing the Dimensionality of Data with Neural Networks

An Autoencoder is a bottleneck architecture that turns a high-dimensional input into a latent low-dimensional code (encoder), and then performs a reconstruction of the input with this latent code (the decoder).

Image: Michael Massi

Source: Reducing the Dimensionality of Data with Neural Networks

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Anomaly Detection 49 7.27%
Time Series 28 4.15%
Denoising 26 3.86%
Self-Supervised Learning 24 3.56%
Disentanglement 16 2.37%
Image Classification 14 2.08%
Dimensionality Reduction 14 2.08%
BIG-bench Machine Learning 13 1.93%
Image Generation 13 1.93%

Components


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

Categories