Denoising Autoencoder Self-Organizing Map (DASOM)

In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex functions. A fundamental approach is the use of higher-level representations devised by restricted Boltzmann machines and (denoising) autoenco...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural networks Jg. 105; S. 112 - 131
Hauptverfasser: Ferles, Christos, Papanikolaou, Yannis, Naidoo, Kevin J.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Elsevier Ltd 01.09.2018
Schlagworte:
Clustering
Denoising autoencoder
Self-organizing map
Unsupervised learning
Visualization
Visualization
Denoising autoencoder
Clustering
Self-organizing map
Unsupervised learning
ISSN:0893-6080, 1879-2782, 1879-2782
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex functions. A fundamental approach is the use of higher-level representations devised by restricted Boltzmann machines and (denoising) autoencoders. We present the Denoising Autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map. In so doing the parameters are adjusted by the proposed unsupervised learning algorithm. The model therefore maintains the clustering properties of its predecessor, whereas by extending and enhancing its visualization capacity enables an inclusion and an analysis of the intermediate representation space. A comprehensive series of experiments comprising optical recognition of text and images, and cancer type clustering and categorization is used to demonstrate DASOM’s efficiency, performance and projection capabilities.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0893-6080
1879-2782
1879-2782
DOI:10.1016/j.neunet.2018.04.016