Utilizing Feature Selection on Higher Order Neural Networks

View Sample PDF

Author(s): Zongyuan Zhao (University of Tasmania, Australia), Shuxiang Xu (University of Tasmania, Australia), Byeong Ho Kang (University of Tasmania, Australia), Mir Md Jahangir Kabir (University of Tasmania, Australia), Yunling Liu (China Agricultural University, China)and Rainer Wasinger (University of Tasmania, Australia)
Copyright: 2017
Pages: 16
Source title: Nature-Inspired Computing: Concepts, Methodologies, Tools, and Applications
Source Author(s)/Editor(s): Information Resources Management Association (USA)
DOI: 10.4018/978-1-5225-0788-8.ch041

Keywords: Artificial Intelligence / Biologically-Inspired Computing / Engineering Science Reference / Medicine & Healthcare

Purchase

View Utilizing Feature Selection on Higher Order Neural Networks on the publisher's website for pricing and purchasing information.

Abstract

Artificial Neural Network has shown its impressive ability on many real world problems such as pattern recognition, classification and function approximation. An extension of ANN, higher order neural network (HONN), improves ANN's computational and learning capabilities. However, the large number of higher order attributes leads to long learning time and complex network structure. Some irrelevant higher order attributes can also hinder the performance of HONN. In this chapter, feature selection algorithms will be used to simplify HONN architecture. Comparisons of fully connected HONN with feature selected HONN demonstrate that proper feature selection can be effective on decreasing number of inputs, reducing computational time, and improving prediction accuracy of HONN.

The IRMA Community

Research IRM

Utilizing Feature Selection on Higher Order Neural Networks

Purchase

Abstract

Related Content

IRMA Sponsors