Abstract
Artificial neural networks constitute a novel class of many-body systems in which the particles are neuron-like units and the interactions are weighted synapse-like connections between these units.1,2 The most extraordinary feature of these systems is that the interactions are subject to modification, depending on the states recently visited by the system. Thus, as the network experiences varied stimuli, knowledge can be stored in the neuron-neuron interactions, for later retrieval in some information-processing task. Indeed, multilayered, feedforward networks of analog neurons can be taught by example to solve complex pat tern-categorization problems using the backpropagation learning algorithm3 or other procedures for modifying connection weights. During the learning process, inner neurons may evolve into useful feature detectors tailored to regularities or correlations inherent in the ensemble of input stimulus patterns and desired output response patterns used for training. The system builds an internal representation, or model, of its pattern environment, which may provide a good approximation to the actual rules determining the underlying input-output map. Accordingly, the artificial neural network may possess a useful generalization or predictive ability, as demonstrated by a high percentage of correct responses when presented with unfamiliar input patterns absent from the training set.
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
B. Müller and J. Reinhardt, Neural Networks — an Introduction, Springer, Heidelberg (1990).
J. W. Clark, “Neural network modelling,” Physics in Medicine and Biology (in press).
D. E. Rumelhart, G. E. Hinton, and R. J. Williams, in Parallel Distributed Processing: Explorations in the Micro structure of Cognition, Vol. 1, D. E. Rumelhart, J. L. McClelland, et al., eds., MIT Press, Cambridge, MA (1986).
H. Bohr, J. Bohr, S. Brunak, R. M. J. Cotterill, B. Lautrup, L. Nøskov, O. H. Olsen, and S. B. Petersen, FEBS Letters B241:223 (1988); N. Qian and T. J. Sejnowski, J. Molec. Biol. 202:865 (1988); H. Bohr, J. Bohr, S. Brunak, R. M. J. Cotterill, H. Fredholm, B. Lautrup, and S. B. Petersen, FEBS Letters 261:43 (1990).
B. Denby, Comput. Phys. Commun. 49:429 (1988); C. Peterson, Nucl. Instr. Methods A279:537 (1989); B. Denby and S. L. Linn, Comput. Phys. Commun. 56:293 (1990); B. Humpert, Comput. Phys. Commun. 56: 299 (1990).
J. R. P. Angel, P. Wizinowich, M. Lloyd-Hart, and D. Sandier, Nature 348:221 (1990); D. Sandier, T. K. Barrett, D. A. Palmer, R. Q. Fugate, and W. J. Wild, Nature 351:300 (1991); S. C. Odenwahn, E. B. Stockwell, R. L. Pennington, R. M. Humphreys, and W. A. Zumach, “Automated star/galaxy discrimination with neural networks,” Ap. J. (in press).
B. Meyer, T. Hansen, D. Nute, P. Albersheim, A. Darvill, W. York, and J. Sellers, Science 251: 542 (1991).
S. Brunak, J. Engelbrecht, and S. Knudsen, J. Molec. Biol. 220 (1991).
J. W. Clark, S. Gazula, and H. Bohr, “Teaching nuclear systematics to neural networks,” in Neural Networks: From Biology to High-Energy Physics, O. Benhar, C. Bosio, P. del Giudice, and E. Tabet, eds., in press.
P. Stolorz, A. Lapedes, and Y. Xia, “Predicting protein secondary structure using neural net and statistical methods,” J. Molec. Biol. (submitted).
D. G. Luenberger, Linear and Nonlinear Programming, Second Edition, Addison-Wesley, Reading, MA (1984).
F. W. Walker, D. G. Miller, and F. Feiner, Chart of the Nuclides, Thirteenth Edition, General Electric, San Jose, CA (1984).
J. W. Clark and S. Gazula, “Artificial neural networks that learn many-body physics,” in Condensed Matter Theories, Vol. 6, S. Fantoni and S. Rosati, eds., Plenum, New York (1991).
S. Gazula, J. W. Clark, and H. Bohr, “Learning and prediction of nuclear stability by neural networks, Nucl. Phys. A (submitted).
W. D. Myers and W. J. Swiatecki, Nucl. Phys. 81:1 (1966).
P. Möller and J. R. Nix, Atomic Data and Nuclear Data Tables 39:213 (1988).
J. W. Clark, S. Gazula, and H. Bohr, “Nuclear phenomenology with neural nets,” in Complex Dynamics in Neural Networks, E. R. Caianiello, J. W. Clark, R. M. J. Cotterill, and J. G. Taylor, eds., Springer, Heidelberg (1992), in press.
P. E. Haustein, Atomic and Nuclear Data Tables 39:185 (1988).
P. J. Masson and J. Jänecke, Atomic and Nuclear Data Tables 39:273 (1988).
M. C. Mozer and P. Smolensky, in Neural Information Processing Systems, Vol. 1, D. Touretzky, ed., Morgan Kaufmann, San Mateo (1989).
Y. Le Cun, J. S. Denker, and S. A. Solla, in Neural Information Processing Systems, Vol. 2, D. Touretzky, ed., Morgan Kaufmann, New York (1990).
A. Bohr and B. R. Mottelson, Nuclear Structure, Vol. I, W. A. Benjamin, New York (1969).
S. G. Thompson and C. F. Tsang, Science 178:1047 (1972).
P. Möller and J. R. Nix, Nucl. Phys. A520:369c (1990).
C. McMillan, M. C. Mozer, and P. Smolensky, “The connectionist scientist game: rule extraction in a neural network,” Proceedings of the Thirteenth Annual Conference of the Cognitive Science Society, Erlbaum, Hilsdale, NJ (1991).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer Science+Business Media New York
About this chapter
Cite this chapter
Clark, J.W., Gazula, S., Gernoth, K.A., Hasenbein, J., Prater, J.S., Bohr, H. (1992). Collective Computation of Many-Body Properties by Neural Networks. In: Ainsworth, T.L., Campbell, C.E., Clements, B.E., Krotscheck, E. (eds) Recent Progress in Many-Body Theories. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-3466-2_24
Download citation
DOI: https://doi.org/10.1007/978-1-4615-3466-2_24
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6535-8
Online ISBN: 978-1-4615-3466-2
eBook Packages: Springer Book Archive