MyJournals Home  

RSS FeedsEntropy, Vol. 20, Pages 927: DBN Structure Design Algorithm for Different Datasets Based on Information Entropy and Reconstruction Error (Entropy)

 
 

8 december 2018 18:00:27

 
Entropy, Vol. 20, Pages 927: DBN Structure Design Algorithm for Different Datasets Based on Information Entropy and Reconstruction Error (Entropy)
 




Deep belief networks (DBNs) of deep learning technology have been successfully used in many fields. However, the structure of a DBN is difficult to design for different datasets. Hence, a DBN structure design algorithm based on information entropy and reconstruction error is proposed. Unlike previous algorithms, we innovatively combine network depth and node number and optimizes them simultaneously. First, the mathematical model of the structural design problem is established, and the boundary constraint for node number based on information entropy is derived by introducing the idea of information compression. Moreover, the optimization objective of the network performance based on reconstruction error is proposed by deriving the fact that network energy is proportional to reconstruction error. Finally, the improved simulated annealing (ISA) algorithm is used to adjust the DBN network layers and nodes simultaneously. Experiments were carried out on three public datasets (MNIST, Cifar-10 and Cifar-100). The results show that the proposed algorithm can design its proper structure to different datasets, yielding a trained DBN which has the lowest reconstruction error and prediction error rate. The proposed algorithm is shown to have the best performance compared with other algorithms and can be used to assist the setting of DBN structural parameters for different datasets.


Del.icio.us Digg Facebook Google StumbleUpon Twitter
 
27 viewsCategory: Informatics, Physics
 
Entropy, Vol. 20, Pages 928: Vector Generation of Quantum Contextual Sets in Even Dimensional Hilbert Spaces (Entropy)
Entropy, Vol. 20, Pages 926: Rolling Element Bearing Fault Diagnosis by Combining Adaptive Local Iterative Filtering, Modified Fuzzy Entropy and Support Vector Machine (Entropy)
 
 
blog comments powered by Disqus


MyJournals.org
The latest issues of all your favorite science journals on one page

Username:
Password:

Register | Retrieve

Search:

Physics

Use these buttons to bookmark us:
Del.icio.us Digg Facebook Google StumbleUpon Twitter


Valid HTML 4.01 Transitional
Copyright © 2008 - 2018 Indigonet Services B.V.. Contact: Tim Hulsen. Read here our privacy notice.
Other websites of Indigonet Services B.V.: Nieuws Vacatures News Tweets Travel Photos Nachrichten Indigonet Finances Leer Mandarijn