Efficient learning in adaptive processing of data structures

Siu Yeung Cho, Zheru Chi, Zhiyong Wang, Wan Chi Siu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

18 Citations (Scopus)

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.
Original languageEnglish
Pages (from-to)175-190
Number of pages16
JournalNeural Processing Letters
Volume17
Issue number2
DOIs
Publication statusPublished - 1 Apr 2003

Keywords

  • Adaptive processing of data structures
  • Backpropagation through structures
  • Long-term dependency problem

ASJC Scopus subject areas

  • Software
  • Neuroscience(all)
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this