eCite Digital Repository

Adaptive Higher Order Neural networks for Effective data Mining

Citation

Xu, S and Chen, L, Adaptive Higher Order Neural networks for Effective data Mining, Sixth International Symposium on Neural Networks (ISNN 2009), 26-29 May 2009, Wuhan, China, pp. 165-173. ISBN 978-3-642-01216-7 (2009) [Refereed Conference Paper]


Preview
PDF
Restricted - Request a copy
87Kb
  

Copyright Statement

The original publication is available at www.springerlink.com

DOI: doi:10.1007/978-3-642-01216-7_18

Abstract

A new adaptive Higher Order Neural Network (HONN) is introduced and applied in data mining tasks such as determining automobile yearly losses and edible mushrooms. Experiments demonstrate that the new adaptive HONN model offers advantages over conventional Artificial Neural Network (ANN) models such as higher generalization capability and the ability in handling missing values in a dataset. A new approach for determining the best number of hidden neurons is also proposed.

Item Details

Item Type:Refereed Conference Paper
Keywords:neural network, higher order neural network, adaptive activation function, data mining
Research Division:Information and Computing Sciences
Research Group:Artificial Intelligence and Image Processing
Research Field:Neural, Evolutionary and Fuzzy Computation
Objective Division:Information and Communication Services
Objective Group:Computer Software and Services
Objective Field:Computer Software and Services not elsewhere classified
Author:Xu, S (Dr Shuxiang Xu)
ID Code:60450
Year Published:2009
Deposited By:Information and Communication Technology
Deposited On:2010-02-05
Last Modified:2015-02-13
Downloads:2 View Download Statistics

Repository Staff Only: item control page