Abstract
Performance of an evolutionary algorithm usually depends on the shape of fitness surface (landscape) defined on the solution space. Hence, learning a geometry of the surface is a very important issue to predict the performance of an evolutionary algorithm. In real world problem, however, it is usually very difficult to know the information of the surface such as the number and distribution of peaks on the surface, the height and width of the peaks and so on. In this paper, we address how we can learn the shape of a peak on the surface by using the fairly well studied Hopfield model of associative memory as a test function.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
J. Komlós, and R. Paturi (1988) Convergence Results in an Associative Memory Model. Neural Networks, 1, pp.239–250.
J. J. Hopfield (1982) Neural Networks and Physical Systems with Emergent Collective Computational Abilities. Proceedings of the National Academy of Sciences, USA, 79, pp.2554–2558.
D. O. Hebb (1949) The Organization of Behavior. Wiley.
S. Wright (1932) The Roles of Mutation, Inbreeding, Crossbreeding and Selection in Evolution. Proceedings of the 6th International Congress of Genetics, pp.356–366.
C. Macken, P. Hagan, and A. Perelson (1991) Evolutionary Walks on Rugged Landscapes. SIAM Journal of Applied Mathematics, 51, pp.799–827.
W. Fontana, and P. Schuster (1987) A Computer Model of Evolutionary Optimization. Biophysical Chemistry, 26, pp.123–147.
J. Maynard Smith (1970) Natural Selection and the Concept of a Protein Space. Nature, 225, pp.563–564.
A. Bray, and M. Moore (1980) Metastable States in Spin Glasses. Journal of Physics C: Solid State Physics 13, pp.L469–L476.
E. D. Weinberger (1990) Correlated and Uncorrelated Fitness Landscapes and How to Tell the Difference. Biological Cybernetics, 63, pp.325–336.
S. A. Kauffman, and S. Levin (1987) Towards a General Theory of Adaptive Walks on Rugged Landscapes. Journal of Theoretical Biology, 128, pp.11–45.
D. C. Mattis (1976) Solvable Spin Systems with Random Interactions. Physics Letters, 56A, pp.421–422.
D. Sherrington, and S. Kirkpatrick (1975) Solvable Model of a Spin Glass. Physical Review Letters, 35, pp.1792–1796.
D. J. Amit (1989) Modeling Brain Function: The World of Attractor Neural Networks. Cambridge University Press.
E. Gardner (1988) The Phase Space of Interactions in Neural Network Models. Journal of Physics, 21A, pp.257–270.
A. Imada, and K. Araki (1995) Genetic Algorithm Enlarges the Capacity of Associative Memory. Proceedings of the 6th International Conference on Genetic Algorithms, pp.413–420.
A. Imada, and K. Araki (1997) Evolution of Hopfield Model of Associative Memory by the Breeder Genetic Algorithm. Proceedings of the 7th International Conference on Genetic Algorithms, pp.784–791.
A. Imada, and K. Araki (1997), Random Perturbations to Hebbian Synapses of Associative Memory using a Genetic Algorithm. Proceedings of International Work-Conference on Artificial and Natural Neural Networks, Springer-Verlag, Lecture Notes in Computer Science, No. 1240, pp.398–407.
A. Imada, and K. Araki (1996) Basin of Attraction of Associative Memory as it Evolves from Random Weights. Proceedings of the 1st Asia-Pacific Conference on Simulated Evolution and Learning, pp.271–278.
D. B. Fogel (1995) Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. IEEE Press.
L. J. Fogel, A. J. Owens, and M. J. Walsh (1966) Artificial Intelligence through Simulated Evolution. Wiley.
T. Jones (1995) Landscapes and Search. Ph.D. dissertation, The University of New Mexico.
B. Manderick, M. de Weger, and P. Spiessens (1993) The GA and the Structure of the Fitness Landscape. Proceedings of the 4th International Conference on Genetic Algorithm, pp128–135.
M. Lipsitch (1993) Adaptation on Rugged Landscapes Generated of Neighboring Genes. Proceedings of the 4th International Conference on Genetic Algorithm, pp143–150.
A. Imada, and K. Araki (1998) Some Statistical Analyses of Fitness Landscape Created by the Hopfield Model of Associative Memory. Proceedings of the International Technical Conference on Circuits/Systems, Computer and Communication, Vol.2, pp1031–1034.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Imada, A. (1999). What does a peak in the landscape of a Hopfield associative memory look like?. In: Mira, J., Sánchez-Andrés, J.V. (eds) Foundations and Tools for Neural Modeling. IWANN 1999. Lecture Notes in Computer Science, vol 1606. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0098192
Download citation
DOI: https://doi.org/10.1007/BFb0098192
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66069-9
Online ISBN: 978-3-540-48771-5
eBook Packages: Springer Book Archive