Abstract
Although recurrent networks can be used as content addressable memories, they can also be used as sequence prediction systems. Because problem solving can often be viewed as a sequence prediction problem, we hypothesize that such networks can be used as problem solvers. There are many aspects to problem solving. Here we concentrate on a single but important aspect, goal finding without search. Using a highly simplified, clearly prototypical version of this problem, a sparsely connected recurrent network successfully predicts novel paths to reach a goal.
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
Amari, S.I. (1972) IEEE Trans. on Computers C-21, 1197–1206.
Hopfield, J. J. (1982) Proc. Natl. Acad. Sci. USA 79, 2554–2558.
Hopfield, J. J. (1984) Proc. Natl. Acad. Sci. USA 81, 3088–3092.
Kleinfeld, D. (1986) Proc. Natl. Acad. Sci. USA 83, 9469–9473.
Levy, W. B (1989) in Computational Models o/Learning in Simple Neural Systems, eds. Hawkins, R. D. & Bower, G. H. ( Academic Press. New York ), pp. 243–305.
Levy, W. B & Steward, O. (1979) Brain Res. 175, 233–245.
Levy, W. B & Steward, O. (1983) Neuro.sci. 8, 791–797.
Levy, W. B, Wu, X. B., & Baxter, R. A. (1995) Intl. J. Neural Svst. 6 (Supp.), 71–80.
Liljenström, H. & Wu. X. B. (1995) Intl. I. Neural Svst. 6, 19–29.
Minai, A. A., Barrows, G., & Levy, W. B (1994) World Congress on Neural Networks IV-176–181
Minai, A. A. & Levy, W. B (1993) In: Advances in Neural Information Processing Systems, eds.
Giles, C. L., Hanson, S. J., & Cowen. J. D. (Morgan Kaufmann. San Mateo, CA), pp. 556–563
Newell, A. & Simon H. (1972) Human Prohlent Solving. Englewood Cliffs, NJ: Prentice-Hall.
Sompolinsky, H. & Kanter. 1.11986) Phis. Rev. Ltrs. 57, 2861–2864.
Wu, X. B.. Baxter, R. A.. & Levy, W. B (1996) Biol. Cvhern. 74, 159–165.
Wu, X. B. & Liljenström, H. (1994) Network: Comput. Neural Svst. 5, 47–60.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer Science+Business Media New York
About this chapter
Cite this chapter
Levy, W.B., Wu, X. (1997). Predicting Novel Paths to Goals by a Simple, Biologically Inspired Neural Network. In: Bower, J.M. (eds) Computational Neuroscience. Springer, Boston, MA. https://doi.org/10.1007/978-1-4757-9800-5_109
Download citation
DOI: https://doi.org/10.1007/978-1-4757-9800-5_109
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4757-9802-9
Online ISBN: 978-1-4757-9800-5
eBook Packages: Springer Book Archive