Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/30193
Title: Efficient learning in adaptive processing of data structures
Authors: Cho, SY
Chi, Z 
Wang, Z
Siu, WC 
Issue Date: 2003
Source: Neural processing letters, 2003, v. 17, no. 2, p. 175-190
Abstract: Many researchers have explored the use of neural network models for the adaptive processing of data structures. The learning formulation for one of the models is known as the Backpropagation Through Structure (BPTS) algorithm. The main limitations of the BPTS algorithm are attributed to the problems of slow convergence speed and long-term dependency. In this Letter, a novel heuristic algorithm is proposed. The idea of this algorithm is to optimize the free parameters of the node representation in data structure by using a hybrid type of learning algorithm. Encouraging results achieved demonstrate that this proposed algorithm outperforms the BPTS algorithm.
Keywords: Adaptive processing of data structures
Backpropagation through structures
Long-term dependency problem
Journal: Neural Processing Letters 
ISSN: 1370-4621
DOI: 10.1023/A:1023680629977
Appears in Collections:Journal/Magazine Article

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

SCOPUSTM   
Citations

18
Last Week
0
Last month
0
Citations as of Feb 6, 2020

WEB OF SCIENCETM
Citations

16
Last Week
0
Last month
0
Citations as of Jul 10, 2020

Page view(s)

114
Last Week
6
Last month
Citations as of Feb 17, 2020

Google ScholarTM

Check

Altmetric


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