Abstract
An autoassociator neural network can be operated to solve a computation problem with a high degree of parallelism. The set of stable states (solutions of the problem) that build up the attractor of such a recurrent network are determined by the feedback weights and biases. This set can be constructed by using the k-out-of-n design rule. It is shown how to convert arbitrary boolean expressions into a list of k-out-of-n constraints. Finally, a compiler for generating the network structure is described.
This is a preview of subscription content, log in via an institution to check access.
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
G. Tagliarmi, J. Christ, E. Page, Optimization Using Neural Networks, IEEE Tr. on Computers, Vol. 40, No. 12, Dec. 1991, 1347–1358
E. Page, G. Tagliarini, Algorithm development for neural networks, Proc. IEEE SPIE, Vol. 880, High Speed Computing, 1988, 11–19
T. Nakagawa, E. Page, G. Tagliarini, SDNN: A Computation Model for Strictly Digital Neural Networks and its Application, Proc. 5th AAAIC’89, ACM/SIGART Dayton, OH, 1989
T. Nakagawa, H. Kitagawa, E. Page, G. Tagliarini, SDNN-3: A Simple Processor Architecture for O(1) Parallel Processing in Combinatorial Optimization with Strictly Digital Neural Networks, IJCNN’91, Singapore Nov. 1991, 2444–2449
H. N. Schaller, On the Problem of Systematically Designing Energy Functions for Neural Expert Systems Based on Combinatorial Optimization Networks, Neuro-Nîmes’92, EC2, Nîmes, 1992, 648–653
D. Tank, J. Hopfield, Collective Computation in Neuronlike Circuits, Scientific American, Dec. 1987, 62–70
D. Tank, J. Hopfield, Simple “Neural” Optimization Networks: An A/D Converter, Signal Decision Circuit, and a Linear Programming Circuit, IEEE Tr. on CAS, Vol. CAS-33, No. 5, May 1986, 533–541
J. Hopfield, D. Tank, “Neural” Computation of Decisions in Optimization Problems, Biol. Cybernetics, Springer, Vol. 52, 1985, 141–152
H. N. Schaller, A collection of constraint design rules for neural optimization networks, in Artificial Neural Networks II: Proc. ICANN’92, Brighton, (Eds.: I. Aleksander, J. Taylor), Elsevier, 1992, 1039–1042
R. K. Brayton, G. D. Hachtel, et. al., Logic Minimization Algorithms for VLSI Synthesis, Kluwer Academic Publishers, 1984
K. Ehrenberger, Automatische Umsetzung von booleschen Funktionen in eine neuronale Struktur, Diplomarbeit, Lehrstuhl für Datenverarbeitung, Technische Universität München, 1992
M. Arai, T. Nakagawa, H. Kitagawa, An Approach to Automatic Test Pattern Generation Using Strictly Digital Neural Networks, IJCNN’92, Baltimore, June 1992, IV-474–479
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag London Limited
About this paper
Cite this paper
Schaller, H.N., Ehrenberger, K. (1993). Defining the Attractor of a Recurrent Neural Network by Boolean Expressions. In: Gielen, S., Kappen, B. (eds) ICANN ’93. ICANN 1993. Springer, London. https://doi.org/10.1007/978-1-4471-2063-6_199
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2063-6_199
Published:
Publisher Name: Springer, London
Print ISBN: 978-3-540-19839-0
Online ISBN: 978-1-4471-2063-6
eBook Packages: Springer Book Archive