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

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Anomaly Detection	44	6.38%
Denoising	39	5.65%
Self-Supervised Learning	26	3.77%
Image Generation	16	2.32%
Clustering	14	2.03%
Semantic Segmentation	14	2.03%
Disentanglement	14	2.03%
Object Detection	13	1.88%
Image Classification	13	1.88%

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

Generative Models