Abstract
The utilization of Genetic Algorithms (GA) in the development of Artificial Neural Networks is a very active area of investigation. The works that are being carried out at present not only focus on the adjustment of the weights of the connections, but also they tend, more and more, to the development of systems which realize tasks of design and training, in parallel. To cover these necessities and, as an open platform for new developments, in this article it is shown a multilevel GA architecture which establishes a difference between the design and the training tasks. In this system, the design tasks are performed in a parallel way, by using different machines. Each design process has associated a training process as an evaluation function. Every design GA interchanges solutions in such a way that they help one each other towards the best solution working in a cooperative way during the simulation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
McCulloch, W. S. & Pitts, W.: “A Logical Calculus of Ideas Immanent in Nervous Activity”. Bulletin of Mathematical Biophysics. No 5. Pp. 115–133. 1943.
Rosenblatt, F.: “The Perceptron: A Probabilistic Model for Information Storage and Oganization in the Brain”. Psylogical Review. No 65. 1958.
Yee, P.: “Clasification Experiments involving Backpropagation and RBF Networks”. Communications Research Laboratory. Report no 249. McMaster university.1992.
Specht, D. F. (1990) “Probabilistic neural networks,” Neural Networks, 3, 110–118.
Dorado, J., Santos, A. y Pazos, A.: “Methodology for the Construction of more Efficient Artificial Neural Networks by Means of Studying and Selecting the Training Set”. International Conference on Neural Networks ICNN96. pp. 1285–1290. 1996.
I. T. Jolliffe, “Principal Component Analysis”, Springer Verlag, 1986.
Williams, R. J. & Zipser, D.: “A Learning Algorithm for Continually Running Fully Recurrent Neural Networks”. Neural Computation no 1. Pp. 270–280. 1989.
Hee Yeal, & y Sung Yan B.: “An Improved Time Series Prediction by Applying the Layerby-Layer Learning Method to FIR Neural Networks”. Neural Networks. Vol. 10 No. 9. Pp. 1717–1729. 1997.
Vassilios Petridis & Athanasios Kehagias: “A Recurrent Network Implementation of Time Series Classification”. Neural Computation. No. 8. Pp. 357–372. 1996.
Montana, D. J. & Davis, L.: “Training Feedforward NN Using Genetic Algorithms”. Proc. of Eleventh International Joint Conference on Artificial Intelligence". Pp. 762–767. 1989.
Joya, G., Frias, J. J., Marín, M. M. & Sandoval, F. (1993): “New Learning Strategies from the Microscopy Level of an ANN”. Electronics Letters. Vol. 29. No 20. Pp. 1775–1777.
Radcliffe, N. J.: “Genetic Set Recombination and its Application to NN Topology Optimization”. Neural Computing and Applications. Vol. 1. No 1. Pp. 67–90. 1993.
A. Pazos, J. Dorado, A. Santos, J. R. Rabuñal y N. Pedreira. “AG paralelo multinivel para el desarrollo de RR.NN.AA.”. CAEPIA-99. Murcia. Spain. 1999.
J. Dorado, A. Santos, A. Pazos, J. R. Rabuñal y N. Pedreira. “Automatic Selection of the Training Set with Genetic Algorithm for Training Artificial Neural Networks”. Gecco 2000. Las Vegas, NV, EE.UU. 2000
McDonnell, J. R. & Waagen, D.: “Evolving Recurrent Perceptrons for Time Series Modeling”. IEEE Transactions on Neural Networks. Vol. 5 No 1. Pp. 24–38. 1996.
Karnin, E. D. (1990): “A Simple Procedure for Pruning Back-Propagation Trained Neural Networks”. IEEE Transactions on Neural Networks. Vol. 1 No 2. Pp. 239–242.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dorado, J., Santos, A., Rabuñal, J.R. (2001). Multilevel Genetic Algorithm for the Complete Development of ANN. In: Mira, J., Prieto, A. (eds) Connectionist Models of Neurons, Learning Processes, and Artificial Intelligence. IWANN 2001. Lecture Notes in Computer Science, vol 2084. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45720-8_86
Download citation
DOI: https://doi.org/10.1007/3-540-45720-8_86
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42235-8
Online ISBN: 978-3-540-45720-6
eBook Packages: Springer Book Archive