By Topic

Training product unit neural networks with genetic algorithms

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Janson, D.J. ; Dept. of Electr. Eng., Idaho Univ., Moscow, ID, USA ; Frenzel, J.F.

Product unit neural networks are useful because they can handle higher order combinations of inputs. When trained using traditional backpropagation, however, they are often susceptible to local minima. The use of genetic algorithm exploratory procedures that can often locate near-optimal solutions to complex problems to overcome this, is discussed. The genetic algorithm maintains a set of trial solutions and forces them to evolve toward an acceptable solution. A representation for possible solutions must first be developed. Then, with an initial random population, the algorithm uses survival of the fittest techniques as well as old knowledge in the gene pool to improve each generation's ability to solve the problem. This improvement is achieved through a four-step process of evaluation, reproduction, breeding, and mutation. An example application is described.<>

Published in:

IEEE Expert  (Volume:8 ,  Issue: 5 )