Two-layer contractive encodings for learning stable nonlinear features

DOI10.1016/J.NEUNET.2014.09.008zbMATH Open1325.68196OpenAlexW2139336101WikidataQ50630147 ScholiaQ50630147MaRDI QIDQ890731FDOQ890731

Authors Hannes Schulz, Tapani Raiko, Sven Behnke, Kyung Hyun Cho

Publication date 11 November 2015

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2014.09.008

zbMATH Keywords

deep learninglinear transformationsemi-supervised learningmulti-layer perceptronpretrainingtwo-layer contractive encoding

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion
• Complex-valued autoencoders
• Why does unsupervised pre-training help deep learning?
• What regularized auto-encoders learn from the data-generating distribution
• Layered Networks for Unsupervised Learning

Cites work

• scientific article; zbMATH DE number 3174791 (Why is no real title available?)
• scientific article; zbMATH DE number 46318 (Why is no real title available?)
• An efficient learning procedure for deep Boltzmann machines
• Enhanced gradient for training restricted Boltzmann machines
• Learning deep architectures for AI
• Multilayer feedforward networks are universal approximators
• On the expressive power of deep architectures
• Reducing the Dimensionality of Data with Neural Networks
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• Why does unsupervised pre-training help deep learning?

Cited in

(2)

• The dynamics of representation learning in shallow, non-linear autoencoders
• Nonredundant sparse feature extraction using autoencoders with receptive fields clustering

Describes a project that uses

Uses Software

• darch
• Hyperopt

This page was built for publication: Two-layer contractive encodings for learning stable nonlinear features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q890731)