Abstract
We propose in this paper an extended model of the random neural networks, whose architecture is multi-feedback. In this case, we suppose different layers where the neurons have communication with the neurons of the neighbor layers. We present its learning algorithm and its possible utilizations; specifically, we test its use in an encryption mechanism where each layer is responsible of a part of the encryption or decryption process. The multilayer random neural network is a stochastic neural model, in this way the entire proposed encryption model has that feature.
Similar content being viewed by others
References
Abdelbaki H, Gelenbe E, Kocak T (1999) Matched neural filters for EMI based mine detection. In: Proceedings of international joint conference on neural networks. IJCNN, Atlanta, p 3236–3240
Aguilar J (2004) A color pattern recognition problem based on the multiple classes random neural network model. Neurocomputing 61: 71–83
Aguilar J (2001) Learning algorithm and retrieval process for the multiple classes random neural network model. Neural Process Lett 13: 81–91
Aguilar J (1998) Definition of an energy function for the random neural to solve optimization problems. Neural Netw 11: 731–738
Aguilar A, Colmenares J (1998) Resolution of pattern recognition problems using a hybrid genetic/random neural network learning algorithm. Pattern Anal Appl 1: 52–61
Aguilar J (2011) Details of the learning procedure for the multilayers random neural network model. Technical report 08-11. CEMISID, Universidad de los Andes, Merida
Atalay V, Gelenbe E, Yalabik N (1992) The random neural network model for texture generation. Int J Pattern Recognit Artif Intell 6: 131–141
Bakircioglu H, Gelenbe E, Kocak T (1997) Image enhancement and fusion with the random neural network. Turk J Electr Eng Comput Sci 5: 65–77
Bakircioglu H, Gelenbe E (1998) Random neural network recognition of shaped objects in strong clutter. In: Proceedings of 3rd conference on applications of artificial neural networks in image processing. Springer, New York, p 22–28
Bakircioglu H, Kocak T (2000) Survey of random neural network applications. Eur J Oper Res 126: 319–330
Basterrech S, Mohammed S, Rubino G, Soliman M (2009) Levenberg–Marquardt training algorithms for random neural networks. Comput J 19: 324–337
Cramer C, Gelenbe E, Gelenbe P (1998) Image and video compression. IEEE Potential 17: 29–33
Fourneau M, Gelenbe E, Suros R (1996) G-networks with multiple classes of negative and positive customers. Theor Comput Sci 155: 141–156
Gelenbe E (1989) Random neural networks with positive and negative signals and product form solution. Neural Netw 1(4): 502–510
Gelenbe E (1991) Theory of the random neural network model. Neural networks: advances and applications. Elsevier, North Holland
Gelenbe E (1993) Learning in the recurrent neural network. Neural Comput 5: 154–164
Gelenbe E, Feng T, Krishnan K (1996) Neural network methods for volumetric magnetic resonance imaging of the human brain. Proc IEEE 84: 1488–1496
Gelenbe E, Kocak T (2004) Wafer surface reconstruction from top-down scanning electron microscope images. Microelectron Eng 75: 216–233
Gelenbe E, Timotheou S (2008) Synchronized intercations in spiked neuronal models. Comput J 51: 723–730
Gelenbe E, Timotheou S (2008) Random neural networks with synchronized interactions. Neural Comput 20: 2308–2324
Georgiopoulos M, Li C, Kocak T (2011) Learning in the feed-forward random neural network: a critical review. Perform Eval 68: 361–384
Halici U, Karaoz E (1996) A linear approximation for the Gelenbe’s learning algorithm for recurrent random neural networks. In: Proceedings of the 6th Turkish symposium on artificial intelligence and neural networks. Springer, New York, p 86–94
Hubert C (1993) Pattern completion with the random neural network using the RPROP learning algorithm. In: Proceedings of international conference on man and cybernetics, vol 2. ICMC, LeTouquet, p 613–617
Hussain K, Moussa G (2005) Laser intensity vehicle classification system based on random neural network. In: Proceedings of 43rd annual southeast regional conference. ACM, New York, p 31–35
Jacobs R (1988) Increased rates of convergence through learning rate adaptation. Neural Netw 1: 151–160
Jordi X (2002) Análisis de redes y sistemas de comunicaciones. Ediciones UPC, Barcelona
Kanter I. (2002) Secure exchange of information by sychronization of neural networks. Europhys Lett 57(1): 141–147
Kiyoharu Y (2004) Advances in multimedia information processing PCM 2004. Springer, Tokyo
Likas A, Stafylopatis A (2000) Training the random neural network using quasi-newton methods. Eur J Oper Res 126: 331–339
NCCS.gov. (2011) National center computional sciences. http://www.nccs.gov/computing-resources/jaguar/. Accessed 3 June 2011
Stallings W (2004) Fundamentos de Seguridad en Redes, Aplicaciones y Estandares. Pearson, Madrid
Stork R, Price K (1997) Differential evolution—a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 11: 341–359
Tanenbaum A (2003) Redes de computadoras. Pearson Educacion, Mexico
Timotheou S (2010) The random neural network: a survey. Comput J 53: 251–267
Triguero J, Guerrero M, Crespo E (2006) Introducción a la criptografía: historia y actualidad. Ediciones de la Universidad de Castilla-La Mancha, Cuenca
Wen Yu J (2006) Cryptography based on delayed chaotic neural networks. Phys Letts 356: 333–338
Zheng Q, Fan Y, Shi Z, Wang Y (2006) Adaptive inertia weight particle swarm optimization. In: Lecture notes in computer science, vol 4029. Springer, Berlin, pp 450–459
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Aguilar, J., Molina, C. The Multilayer Random Neural Network. Neural Process Lett 37, 111–133 (2013). https://doi.org/10.1007/s11063-012-9237-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-012-9237-x