Chapter

Computational Intelligence, Theory and Applications

Volume 33 of the series Advances in Soft Computing pp 599-612

A Feedforward Neural Network based on Multi-Valued Neurons

  • Igor AizenbergAffiliated withDepartment of Computer Science 1, University of Dortmund Email author 
  • , Claudio MoragaAffiliated withDepartment of Computer Science 1, University of Dortmund
  • , Dmitriy PaliyAffiliated withInstitute for Signal Processing TICSP, Tampere University of Technology

* Final gross prices may vary according to local VAT.

Get Access

Abstract

A feedforward neural network based on multi-valued neurons is considered in the paper. It is shown that using a traditional feedforward architecture and a high functionality multi-valued neuron, it is possible to obtain a new powerful neural network. Its learning does not require a derivative of the activation function and its functionality is higher than the functionality of traditional feedforward networks containing the same number of layers and neurons. These advantages of MLMVN are confirmed by testing using Parity n, two spirals and “sonar” benchmarks, and the Mackey-Glass time-series prediction.