Abstract
The statistical mechanical derivation by Simic of the Elastic Net Algorithm (ENA) from a stochastic Hopfield neural network is criticized. In our view, the ENA should be considered a dynamic penalty method. Using a linear distance measure, a Non-equidistant Elastic Net Algorithm (NENA) is presented. Finally, a Hybrid Elastic Net Algorithm (HENA) is discussed.
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
E. Aarts and J. Korst, Simulated Annealing and Boltzmann Machines, A Stochastic Approach to Combinatorial Optimization and Neural Computing, John Wiley & Sons (1989).
R. Durbin and D. Willshaw, An Analogue Approach of the Travelling Salesman Problem Using an Elastic Net Method, Nature, Vol. 326 (1987), pp689–691.
J.H. Geselschap, Een Verbeterd ‘Elastic Net’ Algoritme (An Improved Elastic Net Algorithm), Master’s thesis, Erasmus University Rotterdam, Comp. Sc. Dept., (1994).
J. Hertz, A. Krogh, and R.G. Palmer, Introduction to the Theory of Neural Computation, Addison-Wesley (1991).
J.J. Hopfield, Neural Networks and Physical Systems with Emergent Collective Computational Abilities, Proceedings of the National Academy of Sciences, USA Vol. 79 (1982), pp2554–2558.
G. Parisi, Statistical Field Theory, Addison-Wesley (1988).
C. Peterson and B. Söderberg, Artificial Neural Networks and Combinatorial Optimization Problems, to appear in: Local Search in Combinatorial Optimization, E.H.L. Aarts and J.K. Lenstra eds., John Wiley & Sons.
P.D. Simic, Statistical Mechanics as the Underlying Theory of ‘Elastic’ and ‘Neural’ Optimisations, Network, Vol. 1 (1990), pp88–103.
J. van den Berg and J.C. Bioch, Constrained Optimization with the Hopfield-Lagrange Model, in: Proceedings of the 14th IMACS World Congress (1994), pp470–473.
J. van den Berg and J. C. Bioch, On the (Free) Energy of Stochastic and Continuous Hopfield Neural Networks, in: Neural Networks: The Statistical Mechanics Perspective, J.-H. Oh, C. Kwon, S. Cho eds., World Scientific (1995), pp233–244.
J. van den Berg and J.C. Bioch, Some Theorems Concerning the Free Energy of (Un)Constrained Stochastic Hopfield Neural Networks, in: Lecture Notes in Artificial Intelligence 904, EuroCOLT’95 (1995), pp298–312.
J. van den Berg and J.H. Geselschap, An analysis of various elastic net algorithms, Technical Report EUR-CS-95-06, Erasmus University Rotterdam, Comp. Sc. Dept. (1995).
A.L. Yuille, Generalized Deformable Models, Statistical Physics, and Matching Problems, Neural Computation, Vol. 2 (1990), pp1–24.
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
van den Berg, J., Geselschap, J.H. (1997). A Non-Equidistant Elastic Net Algorithm. In: Ellacott, S.W., Mason, J.C., Anderson, I.J. (eds) Mathematics of Neural Networks. Operations Research/Computer Science Interfaces Series, vol 8. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-6099-9_14
Download citation
DOI: https://doi.org/10.1007/978-1-4615-6099-9_14
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7794-8
Online ISBN: 978-1-4615-6099-9
eBook Packages: Springer Book Archive