GEP Book

  Home
  News
  Author
  Q&A
  Tutorials
  Downloads
  GEP Biblio
  Contacts

  Visit Gepsoft

 

C. FERREIRA 9th Online World Conference on Soft Computing in Industrial Applications, 2004

Designing Neural Networks Using Gene Expression Programming

Introduction
 
An artificial neural network is a computational device that consists of many simple connected units (neurons) that work in parallel. The connections between the units or nodes are weighted usually by real-valued weights. Weights are the primary means of learning in neural networks, and a learning algorithm is used to adjust the weights (e.g., Anderson 1995).

More specifically, a neural network has three different classes of units: input, hidden, and output units. An activation pattern is presented on its input units and spreads in a forward direction from the input units through one or more layers of hidden units to the output units. The activation coming into a unit from other units is multiplied by the weights on the links over which it spreads. All incoming activation is then added together and the unit becomes activated only if the incoming result is above the unit’s threshold.

In summary, the basic elements of a neural network are the units, the connections between units, the weights, and the thresholds. And these are the elements that must be encoded in a linear chromosome so that populations of such structures can adapt in a particular selection environment in order to evolve solutions to different problems.

Over the last decade many systems have been developed that evolve both the topology and the parametric values of a neural network (Angeline et al. 1993; Braun and Weisbrod 1993; Dasgupta and McGregor 1992; Gruau et al. 1996; Koza and Rice 1991; Lee and Kim 1996; Mandischer 1993; Maniezzo 1994; Opitz and Shavlik 1997; Pujol and Poli 1998; Yao and Liu 1996; Zhang and Muhlenbein 1993). The present work introduces a new algorithm, GEP-NN, based on Gene Expression Programming (GEP) (Ferreira 2001) that performs total network induction using linear chromosomes of fixed length (the genotype) that map into complex neural networks of different sizes and shapes (the phenotype). The problems chosen to show the workings of this new algorithm include two problems of logic synthesis: the exclusive-or and the 6-multiplexer.

Home | Contents | Previous | Next