Title
Hardware implementation of random neural networks with reinforcement learning
Keywords
Computer Science, Artificial Intelligence; Computer Science, Theory &; Methods
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.
Journal Title
Artificial Neural Networks - Icann 2006, Pt 1
Volume
4131
Publication Date
1-1-2006
Document Type
Article
Language
English
First Page
321
Last Page
329
WOS Identifier
ISSN
0302-9743; 3-540-38625-4
Recommended Citation
"Hardware implementation of random neural networks with reinforcement learning" (2006). Faculty Bibliography 2000s. 6302.
https://stars.library.ucf.edu/facultybib2000/6302
Comments
Authors: contact us about adding a copy of your work at STARS@ucf.edu