File(s) under permanent embargo
Adaptive Higher Order Neural Networks
This paper introduces an adaptive Higher Order Neural Network (HONN) and applies it in data mining such as Australian credit card assessment. The proposed adaptive HONN model offers significant advantages over conventional Artificial Neural Network (ANN) models such as more accurate predictions and the ability in handling incomplete/missing values in a dataset. A new approach for determining the best number of hidden neurons is also proposed.
History
Publication title
Proceedings of the 2009 WRI Global Congress on Intelligent SystemsEditors
Shang-Ming Zhou, Wenwu WangPagination
26-30ISBN
978-0-7695-3571-5Department/School
School of Information and Communication TechnologyPublisher
IEEE Computer Society Conference Publishing Services (CPS)Place of publication
Los Alamitos, CaliforniaEvent title
WRI Global Congress on Intelligent Systems (GCIS)Event Venue
Xiamen, ChinaDate of Event (Start Date)
2009-05-19Date of Event (End Date)
2009-05-21Rights statement
Copyright © 2009 IEEE.Repository Status
- Restricted