Two-layer contractive encodings for learning stable nonlinear features

DOI10.1016/j.neunet.2014.09.008zbMath1325.68196OpenAlexW2139336101WikidataQ50630147 ScholiaQ50630147MaRDI QIDQ890731

Sven Behnke, Tapani Raiko, Hannes Schulz, 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

linear transformationsemi-supervised learningdeep learningmulti-layer perceptronpretrainingtwo-layer contractive encoding

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Nonredundant sparse feature extraction using autoencoders with receptive fields clustering

Uses Software

• darch
• Hyperopt

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multilayer feedforward networks are universal approximators
• An Efficient Learning Procedure for Deep Boltzmann Machines
• On the Expressive Power of Deep Architectures
• Reducing the Dimensionality of Data with Neural Networks
• Learning Deep Architectures for AI
• Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
• Enhanced Gradient for Training Restricted Boltzmann Machines

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