A Multiobjective Sparse Feature Learning Model for Deep Neural Networks

Hierarchical deep neural networks are currently popular learning models for imitating the hierarchical architecture of human brain. Single-layer feature extractors are the bricks to build deep networks. Sparse feature learning models are popular models that can learn useful representations. But most...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transaction on neural networks and learning systems Ročník 26; číslo 12; s. 3263 - 3277
Hlavní autori: Gong, Maoguo, Liu, Jia, Li, Hao, Cai, Qing, Su, Linzhi
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.12.2015
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Algorithms
Artificial Intelligence
Brain modeling
Computer Simulation
Deep neural networks
evolutionary algorithm
Evolutionary computation
Feature extraction
Humans
Learning - physiology
Linear programming
Models, Theoretical
multiobjective optimization
Neural networks
Neural Networks (Computer)
Pareto optimization
sparse feature learning
Sparsity
multiobjective optimization
Deep neural networks
evolutionary algorithm
sparse feature learning
ISSN:2162-237X, 2162-2388, 2162-2388
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Hierarchical deep neural networks are currently popular learning models for imitating the hierarchical architecture of human brain. Single-layer feature extractors are the bricks to build deep networks. Sparse feature learning models are popular models that can learn useful representations. But most of those models need a user-defined constant to control the sparsity of representations. In this paper, we propose a multiobjective sparse feature learning model based on the autoencoder. The parameters of the model are learnt by optimizing two objectives, reconstruction error and the sparsity of hidden units simultaneously to find a reasonable compromise between them automatically. We design a multiobjective induced learning procedure for this model based on a multiobjective evolutionary algorithm. In the experiments, we demonstrate that the learning procedure is effective, and the proposed multiobjective model can learn useful sparse features.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2015.2469673