Abstract
To recapitulate, there are a great many ways of solving particular problems, a neural network is only one of them. We should stress that the approach is essentially one at the algorithmic level, together with possible implementational consequences in the future. For someone with a specific problem it is first necessary to analyse that problem in terms of the features discussed here, such as whether learning is necessary, generalisation, type of input etc. Such an analysis can provide a pattern against which it should be possible to see if there is a match with one of the architectures in Table 1. If so, that provides a strong suggestion that the matching architecture may prove useful and useable. If no such match exists, it is then possible to ask whether neural networks really are the appropriate tool at all or, alternatively, either to search for the nearest network architecture or for one not mentioned in our scheme.
Preview
Unable to display preview. Download preview PDF.
References
D. Ackley, G. Hinton, and T. Sejnowski (1985) A learning algorithm for Boltzmann machines, Cognitive Science, 9, 147–169.
J.A. Anderson, J.W. Silverstein, S.A. Ritz, and R.S. Jones (1977) Distinctive features, categorical perception, and probability learning: Some applications of a neural model. Psychological Review, 84, 413–451.
A. Barto, R. Sutton and C. Anderson (1983) Neuron-like adaptive elements that can solve difficult learning control problems. IEEE Transactions on Systems, Man, and Cybernetics, SMC-13, 834–846.
G.A. Carpenter and S. Grossberg (1987a) A massively parallel architecture for a selforganizing neural pattern recognition machine. Computer vision, graphics, and image processing, Vol. 37, 54–115.
G.A. Carpenter and S. Grossberg (1987b) ART 2: self-organization of stable category recognition codes for analog input patterns. Applied Optics, Vol. 26, 4919–4930.
G.A. Carpenter, S. Grossberg and J.H. Reynolds (1991) ARTMAP: Supervised realtime learning and classification of nonstationary data by a self-organizing neural network. Neural Networks, Vol. 4, 565–588.
G. Cybenko (1988) Continuous valued neural networks with two hidden layers are sufficient. Technical Report, Department of Computer Science, Tufts University, Medford, MA.
G. Cybenko (1989) Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems, Vol. 2, 303–314.
J.J. Hopfield (1982) Neural networks and physical systems with emergent collective computational properties. Proceedings of the National Academy of Sciences U.S.A., 79, 2554–2558.
J.J. Hopfield and D.W. Tank (1985) “Neural” computation of decisions in optimization problems. Biological Cybernetics, 52, 141–152.
K. Hornik, M. Stinchcombe and H. White (1989) Multilayer feedforward networks are universal approximators. Neural Networks, 2, 359–366.
W. James (1890) Principles of Psychology, New York: Holt.
T. Kohonen (1984) Self-organization and associative memory, Berlin: Springer-Verlag.
B. Kosko (1988) Bidirectional associative memories. IEEE Transactions on Systems, Man, and Cybernetics, SMC-18, 42–60.
Marr (1982) Vision. Freeman, San Francisco.
J.M.J. Murre (1992) Categorization and Learning in Modular Neural Networks. Hemel Hempstead: Harvester Wheatsheaf
J.M.J. Murre, R.H. Phaf and G. Wolters (1992) CALM: Categorizing and Learning Module. Neural Networks, 5, 55–82.
C. Peterson (1990) Parallel distributed approaches to combinatorial optimization: Benchmark studies on Traveling Salesman Problem. Neural Computation 2, 261–269.
C. Peterson and B. Söderberg (1989) A new method for mapping optimization problems onto neural networks. International Journal of Neural Systems 1, 3–22.
F. Rosenblatt (1958) The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 56, 386–408.
D.E. Rumelhart, G.E. Hinton and R.J. Williams (1986) Learning representations by back-propagating errors. Nature, 323, 533–536.
P.K. Simpson (1990) Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations. Pergamon Press, New York, NY.
H. Szu (1986) Fast simulated annealing. In J. Denker (Ed.), AIP Conference Proceedings 151: Neural Networks for Computing, 420–425. New York: American Institute of Physics.
Y. Takefuji and H. Szu (1989) Design of parallel distributed Cauchy Machines. In: Proceedings of the International Joint Conference on Neural Networks, San Diego, CA. Vol. I, 529–532.
B. Widrow (1962) Generalization and information storage in networks of adaline “neurons”. In M. Yovits, G. Jacoby, and G. Goldstein (Eds.), Self-Organizing Systems 1962, 435–461. Washington: Spartan Books.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Hudson, P.T.W., Postma, E.O. (1995). Choosing and using a neural net. In: Braspenning, P.J., Thuijsman, F., Weijters, A.J.M.M. (eds) Artificial Neural Networks. Lecture Notes in Computer Science, vol 931. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0027034
Download citation
DOI: https://doi.org/10.1007/BFb0027034
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59488-8
Online ISBN: 978-3-540-49283-2
eBook Packages: Springer Book Archive