A higher order Hopfield network for vector quantisation

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.

[1]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[2]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[3]  Carsten Peterson,et al.  A New Method for Mapping Optimization Problems Onto Neural Networks , 1989, Int. J. Neural Syst..

[4]  David E. van den Bout,et al.  A traveling salesman objective function that works , 1988, IEEE 1988 International Conference on Neural Networks.

[5]  T. J. Terrell,et al.  Improved block truncation coding using Hopfield neural network , 1991 .

[6]  P. Sadayappan,et al.  Optimization by neural networks , 1988, IEEE 1988 International Conference on Neural Networks.

[7]  Shashank K. Mehta,et al.  An analog neural network to solve the hamiltonian cycle problem , 1993, Neural Networks.

[8]  L. Rabiner,et al.  The acoustics, speech, and signal processing society - A historical perspective , 1984, IEEE ASSP Magazine.

[9]  Sing-Tze Bow,et al.  Pattern recognition. Applications to large data-set problems , 1984 .

[10]  G. Pawley,et al.  On the stability of the Travelling Salesman Problem algorithm of Hopfield and Tank , 2004, Biological Cybernetics.

[11]  William B. Levy,et al.  Determination of parameters in a Hopfield/Tank computational network , 1988, IEEE 1988 International Conference on Neural Networks.

[12]  Sweet.  Determination of parameters in a Hopfield/Tank computational network , 1988 .

[13]  Sanjit K. Mitra,et al.  Alternative networks for solving the traveling salesman problem and the list-matching problem , 1988, IEEE 1988 International Conference on Neural Networks.

[14]  Walter D. Fisher.  On Grouping for Maximum Homogeneity , 1958 .

[15]  X. Xu,et al.  Effective neural algorithms for the traveling salesman problem , 1991, Neural Networks.

[16]  John A. Hartigan,et al.  Clustering Algorithms , 1975 .

[17]  R. Gray,et al.  Vector quantization , 1984, IEEE ASSP Magazine.

[18]  J. Hopfield.  Neurons withgraded response havecollective computational properties likethoseoftwo-state neurons , 1984 .

[19]  Mahesan Niranjan,et al.  A theoretical investigation into the performance of the Hopfield model , 1990, IEEE Trans. Neural Networks.