International Journal of
Physical Sciences

  • Abbreviation: Int. J. Phys. Sci.
  • Language: English
  • ISSN: 1992-1950
  • DOI: 10.5897/IJPS
  • Start Year: 2006
  • Published Articles: 2570

Full Length Research Paper

New activation functions for complex-valued neural network

Hamid A. Jalab1* and Rabha W. Ibrahim2
  1Department of Computer System and Technology, Faculty of Computer Science and Information Technology, University Malaya, 50603 Kuala Lumpur, Malaysia. 2School of Mathematical Sciences, Faculty of Science and Technology, Universiti Kebangsaan Malaysia, Bangi 43600, Selangor Darul Ehsan, Malaysia.
Email: [email protected]

  •  Accepted: 14 March 2011
  •  Published: 04 April 2011

Abstract

 

This paper presents a new types of complex-valued sigmoid function for a fully multi-layered complex-valued neural network (CVNN). By using the concept of the subordination between analytic functions in open disc, we able to study the reducibility of CVNN. A real-world problem example has been used as a classifier. The simulations results reveal that the proposed fully complex-valued network, been better trained reduces the testing time by 54% compared to the choice of using the traditional sigmoid activation function.

 

Key words: Complex valued neural network, activation functions, reducibility, irreducibility, subordination.