Extending memory in the neuromic array
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The authors describe an algorithm which stores information and provides a learning capability. This algorithm is affiliated with a class of neural networks which are referred to as neuromic arrays. The algorithms may be viewed as a generalized training procedure for the affiliated networks. The algorithm is demonstrated via simulation for several binary vectoral training sets. It is shown that the binary universe (-1,1)/sup n/ can be taken as the training set. Simulations which demonstrate learning for the n=4, 6, 8 cases are presented. The problem of subdividing the binary universe into a disjoint cover of training subsets is considered. Simulations are used to explore the robustness and recognition performance of the training algorithm when applied to the binary universe and/or its disjoint covers.Keywords
This publication has 9 references indexed in Scilit:
- Non-binary neural networksPublished by Springer Nature ,2006
- Bicameral neural computingPublished by Springer Nature ,2006
- Generalized distributive memory arraysPublished by Springer Nature ,2006
- A clustering algorithm for vector valued processesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Using polynomic embedding for neural network designIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1992
- Design Of A High Order Neural Network Motion SensorPublished by SPIE-Intl Soc Optical Eng ,1989
- Multiconnected neural network modelsJournal of Physics A: General Physics, 1987
- Machine Learning Using a Higher Order Correlation NetworkPhysica D: Nonlinear Phenomena, 1986
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982