A STRUCTURE-PARAMETER-ADAPTIVE (SPA) NEURAL TREE FOR THE RECOGNITION OF LARGE CHARACTER SET

Authors
LI T TANG YY FANG LY
Citation
T. Li et al., A STRUCTURE-PARAMETER-ADAPTIVE (SPA) NEURAL TREE FOR THE RECOGNITION OF LARGE CHARACTER SET, Pattern recognition, 28(3), 1995, pp. 315-329
Citations number
29
Categorie Soggetti
Computer Sciences, Special Topics","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence
Journal title
Pattern recognition → ACNP
ISSN journal
00313203
Volume
28
Issue
3
Year of publication
1995
Pages
315 - 329
Database
ISI
SICI code
0031-3203(1995)28:3<315:AS(NTF>2.0.ZU;2-P
Abstract
An adaptive self-organizing neural tree called the structure-parameter -adaptive (SPA) neural tree is presented in this paper. The SPA neural tree can adapt to a changing environment parametrically and structura lly. The SPA neural tree grows when new concepts are learned and shrin ks when old concepts are disposed. It also makes parameter adaptation to cope with small changes in the environment. The SPA neural tree is suited to hierarchical classification. Its application to character pa ttern recognition is also presented in this paper. When applied to cha racter pattern recognition, it shows promising performance.