Replicator neural networks for universal optimal source coding.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, background): “Although the term autoencoder is the most popular nowadays, they were also known as autoassociative neural networks [38], diabolo networks [39] and replicator neural networks [40].”
Deep belief networks (2009, background): “It is difficult, however, to optimize the weights in non-linear autoencoders that have multiple hidden layers with many million parameters [3, 5].”
Advances in Nonlinear Blind Source Separation (2003, background): “Hecht-Nielsen [90], [91] proposed so-called replicator networks for universal optimal nonlinear coding of input data.”
Outlier Detection Using Replicator Neural Networks (2002, methodology): “The RNN approach has linear analogues in Principal Components Analysis [10].”
A comparative study of RNN for outlier detection in data mining (2002, methodology): “Replicator neural networks have been used in image and speech processing for their data compression capabilities [6, 16].”
Fake Twitter followers detection by denoising autoencoder (2017, background): “Autoencoders are designed explicitly to have an output as similar as possible to the input, creating a compression of the data inside the network itself [18], [25].”