Abstract
A higher order version of the Hopfield neural network is presented which will perform a simple vector quantisation or clustering function. This model requires no penalty terms to impose constraints in the Hopfield energy, in contrast to the usual one where the energy involves only terms quadratic in the state vector. The energy function is shown to have no local minima within the unit hypercube of the state vector so the network only converges to valid final states. Optimisation trials show that the network can consistently find optimal clusterings for small, trial problems and near optimal ones for a large data set consisting of the intensity values from a digitised, grey- level image.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Hopfield JJ, Tank DW. Neural computation of decisions in optimization problems. Biol Cybernetics 1985; 52: 141–152
Wilson GV, Pawley PS. On the stability of the Traveling Salesman Problem algorithm of Hopfield and Tank. Biol Cybernetics 1988; 58: 63–70
Aiyer SVB, Niranjan M, Fallside F. A theoretical investigation into the performance of the Hopfield model. IEEE Trans Neural Networks 1990; 1: 204–215
Ramanujam J, Sadayappan P. Optimisation by neural networks. Proc IEEE Int Conf Neural Networks, San Diego, CA, 1988; 2: 325–332
Brandt RD, Wang Y, Laub AJ, Mitra SK. Alternative networks for solving the Traveling Salesman Problem and the List-Matching Problem. Proc IEEE Int Conf Neural Networks, San Diego, CA, 1988; 2: 333–340
Peterson C, Soderberg B. A new method for mapping optimization problems onto neural networks. Int J Neural Systems 1989; 1: 3–22
Xu X, Tsai WT. Effective neural algorithms for the Traveling Salesman Problem. Neural Networks 1991; 4: 193–205
Gray RM. Vector quantization. IEEE ASSP Magazine 1984; 1: 4–29
Van den Bout DE, Miller TK. A traveling salesman objective function that works. Proc IEEE Int Conf Neural Networks, San Diego, CA, 1988; 2: 299–303
Hegde SU, Sweet JL, Levy WB. Determination of parameters in a Hopfield/Tank computational network. Proc IEEE Int Conf Neural Networks, San Diego, CA, 1988; 2: 291–298
Bow Sing-Tze. Pattern Recognition: Applications to Large Data-Set Problems. Marcel Dekker, 1984
Qiu G, Varley MR, Ferrell TJ. Improved block truncation coding using a Hopfield neural network. Electr Lett 1991; 27(21): 1924–1926
Hopfield JJ. Neurons with graded response have collective computational properties like those of two-state neurons. Proc Nat Acad Sci USA 1984; 81: 3088–3092
Goldberg DE. Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, 1989
Fisher WD. On grouping for maximum homogeneity. J Am Stat Assoc 1958; 53
Hartigan JA. Clustering Algorithms. John Wiley and Sons, 1975
Mehta S, Fulop L. An analog neural network to solve the Hamiltonian Cycle Problem. Neural Networks 1993; 6: 869–881
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Soper, A. A higher order Hopfield network for vector quantisation. Neural Comput & Applic 7, 99–106 (1998). https://doi.org/10.1007/BF01414161
Issue Date:
DOI: https://doi.org/10.1007/BF01414161