SOME APPLICATIONS OF CLUSTERING IN THE DESIGN OF NEURAL NETWORKS

被引：13

作者：

GOPALAKRISHNAN, M ^{[1
]}

SRIDHAR, V ^{[1
]}

KRISHNAMURTHY, H ^{[1
]}

机构：

[1] INDIAN INST SCI,SUPERCOMP EDUC & RES CTR,BANGALORE 560012,KARNATAKA,INDIA

来源：

PATTERN RECOGNITION LETTERS | 1995年 / 16卷 / 01期

关键词：

BACK PROPAGATION; CLUSTERING; NEURAL NETWORKS; RADIAL BASIS FUNCTIONS; TRAINING ALGORITHMS;

D O I：

10.1016/0167-8655(94)00064-A

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we discuss the role of clustering techniques in the design of neural networks. Specifically, we address the issue in relation to two network paradigms: one based on back-propagation and the other based on radial basis functions. In the former case, we demonstrate, emprically, that by employing clustering techniques, the training effort may be drastically brought down. In the latter case, we demonstrate that clustering techniques can be employed to build more robust classifiers. We also discuss the role of clustering in the design of hierarchical systems. Specifically, we discuss a hierarchical system based on radial basis functions.

引用

页码：59 / 65

页数：7

共 18 条

[1]

Anderberg, Cluster Analysis for Applications, (1973)

[2]

Beale, Jackson, Neural Computing: An Introduction, (1990)

[3]

Duda, Hart, Pattern Classification and Scene Analysis, (1973)

[4]

Gopalakrishnan, Sridhar, Krishnamurthy, A neural network based Tamil character recognition system, Proc. Internat. Conf. on South-Asian Languages, (1994)

[5]

Hush, Horne, Progress in supervised neural networks, IEEE Signal Processing Magazine, (1993)

[6]

Jain, Dubes, Algorithms for Clustering, (1988)

[7]

Kung, Digital Neural Networks, (1993)

[8]

Lee, Chang, Applications of minimal spanning tree for information storage, Proc. Internat. Symposium on Chinese Input/Output Systems, pp. 1245-1256, (1973)

[9]

Lee, Slagle, Mong, Towards automatic auditing of records, IEEE Transactions on Software Engineering, 4, 5, pp. 441-448, (1978)

[10]

Michalsky, Knowledge acquisition through conceptual clustering: Theoretical framework and an algorithm for partitioning data into conjunctive concepts, Internat. J. Policy and Information Systems, 4, 3, pp. 219-244, (1980)

← 1 2 →