Authors:
Heng Ma
;
Yonggang Lu
and
Haitao Zhang
Affiliation:
Lanzhou University, China
Keyword(s):
Deep Learning, Autoencoder, Architecture Optimization, Correlation Analysis.
Related
Ontology
Subjects/Areas/Topics:
Adaptive Architectures and Mechanisms
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Learning Paradigms and Algorithms
;
Methodologies and Methods
;
Neural Networks
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Theory and Methods
Abstract:
Currently, deep learning has already been successfully applied in many fields such as image recognition, recommendation systems and so on. Autoencoder, as an important deep learning model, has attracted a lot of research interests. The performance of the autoencoder can greatly be affected by its architecture. How-ever, how to automatically determine the optimal architecture of the autoencoder is still an open question. Here we propose a novel method for determining the optimal network architecture based on the analysis of the correlation of the network weights. Experiments show that for different datasets the optimal architecture of the autoencoder may be different, and the proposed method can be used to obtain near optimal network architecture separately for different datasets.