Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/24077
Title: Partially connected feedforward neural networks on Apollonian networks
Authors: Wong, WK 
Guo, ZX
Leung, SYS 
Keywords: Apollonian networks
Feedforward neural networks
Partially connected neural networks
Randomly connected neural networks
Issue Date: 2010
Publisher: North-Holland
Source: Physica A. Statistical mechanics and its applications, 2010, v. 389, no. 22, p. 5298-5307 How to cite?
Journal: Physica A. Statistical mechanics and its applications 
Abstract: This paper presents a novel and data-independent method to construct a type of partially connected feedforward neural network (FNN). The proposed networks, called Apollonian network-based partially connected FNNs (APFNNs), are constructed in terms of the structures of two-dimensional deterministic Apollonian networks. The APFNNs are then applied in various experiments to solve function approximation, forecasting and classification problems. Their results are compared with those generated by partially connected FNNs with random connectivity (RPFNNs), different learning algorithm-based traditional FNNs and other benchmark methods. The results demonstrate that the proposed APFNNs have a good capacity to fit complicated input and output relations, and provide better generalization performance than traditional FNNs and RPFNNs. The APFNNs also demonstrate faster training speed in each epoch than traditional FNNs.
URI: http://hdl.handle.net/10397/24077
ISSN: 0378-4371
EISSN: 1873-2119
DOI: 10.1016/j.physa.2010.06.061
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

3
Last Week
0
Last month
0
Citations as of Oct 10, 2017

WEB OF SCIENCETM
Citations

2
Last Week
0
Last month
0
Citations as of Oct 15, 2017

Page view(s)

40
Last Week
6
Last month
Checked on Oct 15, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.