Abstract
Gelenbe has proposed a neural network, called a Random Neural Network, which calculates the probability of activation of the neurons in the network. In this paper, we propose to solve the patterns recognition problem using a hybrid Genetic/Random Neural Network learning algorithm. The hybrid algorithm trains the Random Neural Network by integrating a genetic algorithm with the gradient descent rule-based learning algorithm of the Random Neural Network. This hybrid learning algorithm optimises the Random Neural Network on the basis of its topology and its weights distribution. We apply the hybrid Genetic/Random Neural Network learning algorithm to two pattern recognition problems. The first one recognises or categorises alphabetic characters, and the second recognises geometric figures. We show that this model can efficiently work as associative memory. We can recognise pattern arbitrary images with this algorithm, but the processing time increases rapidly.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Chen D, Giles C, Sun S, Chen H, Less Y, Goudreau M. Constructive learning of recurrent neural network. Proceedings IEEE International Conference Neural Networks 1993; 1196–1201
Maniezzo V. Genetic evolution of the topology and weight distribution of neural networks. IEEE Transactions Neural Networks 1994; 5(1):39–53
Hung S, Adeli H. A parallel genetic/neural network learning algorithm for MIMD shared memory machines. IEEE Transactions Neural Networks 1994; 5(6): 900–909
Gelenbe E. Learning in the recurrent Random Neural Network. Neural Computation 1993; 5(5): 584–596
Aguilar J. A recognition algorithm using the Random Neural Network. Proceedings 3rd International Congress on Computer Science Research 1996; 16–20
Fogel D, Fogel L, Porto V. Evolving neural networks. Biological Cybernetics 1990; 63: 487–493
Angeline P, Saunders G, Pollack J. An evolutionary algorithm that constructs recurrent neural network. IEEE Transactions Neural Network 1994; 5(1): 54–64
Aguilar J. Evolutionary learning on Recurrent Random Neural Network: Proceedings World Congress on Neural Networks 1995; 232–236
Gelenbe E. Random neural networks with positive and negative signals and product form solution. Neural Computation 1989; 1(4): 502–510
Gelenbe E. Stable random neural networks. Neural Computation 1990; 2(2): 239–247
Gelenbe E, Stafylopatis A, Likas A. Associative memory operation of the Random Network Model. Proceedings International Conference Artificial Neural Networks (ICANN 91) 1991; 307–315
Aguilar J. Using the general energy function of the Random Neural Networks to solve the graph partitioning problem. Proceedings IEEE International Conference Neural Networks 1996; 2130–2135
Aguilar J. A general method to solve combinatorial optimization problems with the Random Neural Networks. In: Cerrolaza M, Gajardo C, Brebbia C. (eds), Numerical Methods in Engineering Simulation. Computational Mechanics Publications, 1996; 349–356
Aguilar J. An energy function for the Random Neural Networks. Neural Processing Letters 1996; 4: 17–27
Aguilar J, Colmenares A. Recognition algorithm using evolutionary learning on the Random Neural Networks. Proceedings IEEE International Conference Neural Networks 1997; 1023–1028
Aguilar J. An approach for combinatorial optimization problem based on learning in the recurrent random neural network. Proceedings World Congress on Neural Networks 1994; 420–425
Mulhenbein H, Ceorges-Schleuter M, Kramer O. Evolution algorithms in combinatorial optimization. Parallel Computing 1988; 7(1): 65–88
Golberg D. Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, 1989
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Aguilar, J., Colmenares, A. Resolution of pattern recognition problems using a hybrid Genetic/Random Neural Network learning algorithm. Pattern Analysis & Applic 1, 52–61 (1998). https://doi.org/10.1007/BF01238026
Received:
Revised:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF01238026