Abstract
In this paper, we present a hardware implementation of a random neural network (RNN) model. The RNN, introduced by Gelenbe, is a spiked neural network model that possesses several mathematical properties such as the existence and uniqueness of the solution, and convergence of the learning algorithm. In particular, we discuss the implementation details for an RNN which uses a reinforcement learning algorithm. We also illustrate an example where this circuit implementation is used as a building block in a recently proposed novel network routing protocol called cognitive packet networks (CPN). CPN does not employ a routing table instead it relies on the RNN with a reinforcement algorithm to route probing packets.
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
Gelenbe, E.: Random neural networks with negative and positive signals and product form solution. Neural Computation 1(4), 502–511 (1989)
Gelenbe, E.: Stability of the random neural network model. Neural Computation 2(2), 239–247 (1990)
Gelenbe, E.: Learning in the recurrent random neural network. Neural Computation 5(1), 154–164 (1993)
Gelenbe, E., Mao, Z.-H., Li, Y.-D.: Function approximation with spiked random networks. IEEE Trans. on Neural Networks 10(1), 3–9 (1999)
Bakircioglu, H., Kocak, T.: Survey of random neural network applications. European Journal of Operational Research 126, 319–330 (2000)
Halici, U.: Reinforcement learning algorithm with internal expectations for the random neural network. European Journal of Operations Research 126, 288–307 (2000)
Gelenbe, E., Lent, R., Xu, Z.: Design and analysis of cognitive packet networks. Performance Evaluation 46, 155–176 (2001)
Seeber, J.: Design and implementatation of smart packet processor for the cognitive packet network router. M.S. Thesis, University of Central Florida, Orlando (2002)
Gelenbe, E., Lent, R., Nunez, A.: Self-aware networks and QoS. Proc. of the IEEE 9(9), 1478–1489 (2004)
Gelenbe, E.: Cognitive Packet Network. U.S. Patent No. 6,804,201 B1 (October 12, 2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kocak, T. (2006). Hardware Implementation of Random Neural Networks with Reinforcement Learning. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds) Artificial Neural Networks – ICANN 2006. ICANN 2006. Lecture Notes in Computer Science, vol 4131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11840817_34
Download citation
DOI: https://doi.org/10.1007/11840817_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-38625-4
Online ISBN: 978-3-540-38627-8
eBook Packages: Computer ScienceComputer Science (R0)