Abstract
As may be evident from the previous section, optimisation networks provide an attractive method for solving combinatorial optimisation problems. Although the original HT network has a limited applicability, new formulations may extend this applicability considerably. Combination with traditional approaches (e.g., Burke, 1994) may also improve solution quality and speed. The combination of the Potts networks with simulated annealing seems to provide the best of both worlds: improved speed over the HT network and the performance (ability to escape from local minima) of simulated annealing techniques (e.g., as in Boltzmann Machines). The Potts network and elastic net approaches show good performance up to large-sized problems. In addition they can be treated formally in terms of statistical mechanics (Peterson and Söderberg, 1989; Simic, 1990). Further improvements of these optimisation networks are to be expected in the near future. Additionally, the availability of parallel hardware may facilitate real-time application of optimisation networks (e.g., Wang, 1994).
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Y. Akiyama, A. Yamashita, M. Kajiura and H. Aiso (1989) Combinatorial optimization with Gaussian Machines. In: Proceedings of the International Joint Conference on Neural Networks, Vol. I, San Diego, CA, 533–540.
S-I. Amari (1977) A neural theory of association and concept formation. Biological Cybernetics 26, 175–185.
D.J. Amit (1989) Modeling brain function: The world of attractor neural networks. Cambridge University Press, Cambridge.
L.I. Burke (1994) Neural methods for the traveling salesman problem: insights from operations research. Neural Networks 7, 681–690.
M.A. Cohen and S. Grossberg (1983) Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Transaction on Signals, Machines and Cybernetics 13, 815–826.
R. Durbin and D. Willshaw (1987) An analogue approach to the travelling salesman problem using an elastic net method. Nature 326, 689–691.
S. Grossberg (1973) Contour enhancement, short term memory, and constancies in reverberating neural networks. Studies in Applied Mathematics LII, 213–257.
S. Grossberg (Ed.) (1982) Studies of mind and brain: neural principles of learning, perception, development, cognition, and motor control, Boston, Reidel Press.
S. Grossberg (1988) Nonlinear neural networks: principles, mechanisms, and architectures. Neural Networks 1, 17–61.
J. Hertz, A. Krogh, and R.G. Palmer (1991) Introduction to the theory of neural computation. Redwood City CA: Addison-Wesley Publishing Company.
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 (1984) Neurons with graded response have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Sciences U.S.A. 81, 3088–3092.
J.J. Hopfield and D.W. Tank (1985) “Neural” computation of decisions in optimization problems. Biological Cybernetics 52, 141–152.
A. Joppe, H.R.A. Cardon and J.C. Bioch (1990) A neural network for solving the travelling salesman problem on the basis of city adjacency in the tour. In: Proceedings of the International Neural Network Conference, Paris, Vol. 1, 254–257.
S. Kirkpatrick, C.D. Gelatt and M.P. Vecchi (1983) Optimization by simulated annealing. Science 220, 671–680.
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.
E.O. Postma, H.J. Van den Herik, and P.T.W. Hudson (1993) Activity-conserving dynamics for neural networks. In S. Gielen and B. Kappen (Eds.), Proceedings of the International Conference on Artificial Neural Networks, ICANN'93 Springer-Verlag, London, 539–544.
P. D. Simic (1990) Statistical mechanics as the underlying theory of ‘elastic’ and ‘neural’ optimisations. Network 1, 89–103.
Y. Takefuji and H. Szu (1989) Design of parallel distributed Cauchy Machines. In: Proceedings of the International Joint Conference on Neural Networks, Vol. I, San Diego, CA, 529–532.
D.W. Tank and J.J. Hopfield (1987) Collective computation in neuronlike circuits. Scientific American 257 (6), 62–70.
D.E. Van den Bout and T.K. Miller III (1989) Graph partitioning using annealing neural networks. In: Proceedings of the International Joint Conference on Neural Networks, Vol. I, San Diego, CA, 521–528.
J. Wang (1994) A deterministic annealing neural network for convex programming. Neural Networks 7, 629–641.
G.V. Wilson and G.S. Pawley (1988) On the stability of the traveling salesman problem algorithm of Hopfield and Tank. Biological Cybernetics 58, 63–70.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Postma, E.O. (1995). Optimisation networks. 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/BFb0027028
Download citation
DOI: https://doi.org/10.1007/BFb0027028
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