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...
Saved in:
Published in | Neural Information Processing pp. 335 - 341 |
---|---|
Main Authors | , , , |
Format | Book Chapter |
Language | English |
Published |
Cham
Springer International Publishing
|
Series | Lecture Notes in Computer Science |
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |