Synthesis of GBSB-based Neural Associative Memories Using Evolution Program

  • Hyuk Cho (Department of Computer Science, Korea University, Chochiwon) ;
  • Park, Joo-young (Department of Control and Instrumentation Engineering, Korea University) ;
  • Moon, Jong-sub (Department of Electronic and information Engineering, Korea University, Chochiwon) ;
  • Park, Dai-hee (Department of Computer Science, Korea University, Chochiwon)
  • Published : 2001.12.01

Abstract

In this paper, we propose a reliable method for searching the optimally performing generalized brain-state-in-a-box (GBSB) neural associative memory using an evolution program (EP) given a set of prototype patterns to be stored as stable equilibrium points. First, we exploit some qualitative guidelines necessary to synthesize the GBSB model. Next, we parameterize the solution space utilizing the limited number of parameters to represent the solution space. Then, we recast the synthesis of GBSB neural associative memories as two constrained optimization problems, which are equivalent to finding a solution to the original synthesis problem. Finally, we employ an evolution program (EP), which enables us to find an optimal set of parameters related to the size of domains of attraction (DOA) for prototype patterns. The validity of this approach is illustrated by a design example and computer simulations.

Keywords

References

  1. Psychological Review v.84 Distinctive features, categorical perception, and probability learning: some applications of a neural model Anderson, J. A.;Silverstein, J. W.;Ritz, S. A.;Jones, R. S.
  2. IEEE Transactions on Systems, Man and Cybernetics v.13 Absolute stability of global pattern formulation and parallel memory storage by competitive neural networks Cohen, M. A.;Grossberg, S.
  3. IEEE Transactions on Neural Networks v.8 On neural networks that design neural associative memories Chan, H. Y.;Zak, S. H.
  4. Ph. D. dissertation, Department of Computer and Communications Sciences, University of Michigan An analysis of the Behavior of a Class of Genetic Adaptive Systems De Jong, K. A.
  5. Genetic Algorithms in Search, Optimization, and Machine Learning Goldberg, D. E.
  6. Journal of Mathematical Psychology v.37 Stability and optimization analysis of the generalized brain-state-in-a-box neural network model Golden, R. M.
  7. Matrix Computations(3rd ed.) Golub, G. H.;Van Loan, C. F.
  8. Neural networks: A Comprehensive Foundation Haykin, S.
  9. Proceedings of National Academy of Sciences v.79 Neural networks and physical systems with emergent collective computational abilities Hopfield, J. J.
  10. IEEE Transaction on Neural Networks v.3 Dynamical analysis of the brain-state-in-a-box (BSB) neural models Hui, S.;Zak, S. H.
  11. IEEE Transactions on Neural Networks v.5 Synthesis of brain-state-in-a-box (BSB) based associative memories Lillo, W. E.;Miller, D. C.;Hui, S.;Zak, S. H.
  12. Phaysical Review v.A40 Dynamics of iterated-map neural networks Marcus, C. M;Westervelt, R. M.
  13. Genetic Algorithms + Data Structures = Evolution Programs(2nd edition) Michalewicz, Z.
  14. IEEE Control Systems Magazine v.10 Associative memories via artificial neural networks Michel, A. N.;Farrell, J. A.
  15. IEEE Transactions on Neural Networks v.2 Analysis and synthesis of a class of discrete-time neural networks described on hypercubes Michel, A. N.;Si, J.;Yen, G.
  16. An Introduction to Genetic Algorithms Mitchell, M.
  17. IEEE Transactions on Neural Networks v.10 no.4 Design of GBSB Neural Associative Memories Using Semidefinte Programming Park, J.;Cho, H.;Park, D.
  18. IEEE Transactions on Neural Networks v.6 A synthesis procedure for brain-state-in-a-box neural networks Perfetti, R.
  19. Proc. 3rd Int. Conf. Genetic Algorithms A study of control parameters affecting online performance of genetic algorithms for function optimization Schaffer, J. D.;Caruana, R. A.;Eshelman, L. J.;Da, R.
  20. IEEE Transactions on Computers v.42 no.5 A Neural-Weighted Learning Algorithm and Its Hardware Implementation in Associative Memories Wang, T.;Zhuang, X.;Xing, X.;Xiao, X.
  21. Neural Networks v.9 Improving Recall in Associative Memories by Dynamic Threshold Wang, T.
  22. Neural Networks v.9 no.3 Asymmetric Hopfield-type networks: Theory and Applications Xu, Z. B.;Hu, G. Q.;Kwong, C. P.
  23. Proceedings of 1995 World Congress on Neural Networks Unlearning algorithm in associative memory Yen, G. G.
  24. Neural Networks v.9 Learning and forgetting in generalized brain-state-in-a-box (BSB) neural associative memories Zak, S. H.;Lillo, W. E.;Hui, S.