Hierarchical hybrid fuzzy-neural networks for approximation with mixed input variables

Di Wang, Xiao Jun Zeng, John A. Keane

Research output: Contribution to journalArticlepeer-review

15 Scopus citations

Abstract

Real-world systems usually involve both continuous and discrete input variables. However, in existing learning algorithms of both neural networks and fuzzy systems, these mixed variables are usually treated as continuous without taking into account the special features of discrete variables. It is inefficient to represent each discrete input variable having only a few fixed values by one input neuron with full connection to the hidden layer. This paper proposes a novel hierarchical hybrid fuzzy neural network to represent systems with mixed input variables. The proposed model consists of two levels: the lower level are fuzzy sub-systems each of which aggregates several discrete input variables into an intermediate variable as its output; the higher level is a neural network whose input variables consist of continuous input variables and intermediate variables. For systems or function approximations with mixed variables, it is shown that the proposed hierarchical hybrid fuzzy neural networks outperform standard neural networks in accuracy with fewer parameters, and both provide greater transparency and preserve the universal approximation property (i.e., they can approximate any function with mixed input variables to any degree of accuracy).

Original languageBritish English
Pages (from-to)3019-3033
Number of pages15
JournalNeurocomputing
Volume70
Issue number16-18
DOIs
StatePublished - Oct 2007

Keywords

  • Approximation
  • Fuzzy systems
  • Hierarchical structure
  • Hybrid systems
  • Neural networks

Fingerprint

Dive into the research topics of 'Hierarchical hybrid fuzzy-neural networks for approximation with mixed input variables'. Together they form a unique fingerprint.

Cite this