Fuzzy Signature Neural Networks for Classification: Optimising the Structure

We construct fuzzy signature neural networks where fuzzy signatures replace hidden neurons in a neural network similar to a radial basis function neural network. We investigated the properties of a naïve and a principled approach to fuzzy signature construction. The naïve approach provides very good...

Full description

Saved in:
Bibliographic Details
Published inNeural Information Processing pp. 335 - 341
Main Authors Gedeon, Tom, Zhu, Xuanying, He, Kun, Copeland, Leana
Format Book Chapter
LanguageEnglish
Published Cham Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
clustering
diabetes
fuzzy signature
neural network
RBF
salary selection
Online AccessGet full text

Cover

More Information
Summary:We construct fuzzy signature neural networks where fuzzy signatures replace hidden neurons in a neural network similar to a radial basis function neural network. We investigated the properties of a naïve and a principled approach to fuzzy signature construction. The naïve approach provides very good results on benchmark datasets, but is outperformed by the principled approach when we approximate the noisy nature of real world datasets by randomly eliminating 20% of the data. The major benefit of the principled approach is to substantially improve robustness of the fuzzy signature neural networks we produce.
ISBN:3319126369
9783319126364
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-12637-1_42