Improving convergence and solution quality of Hopfield-type neural networks with augmented Lagrange multipliers

@article{Li1996ImprovingCA,
  title={Improving convergence and solution quality of Hopfield-type neural networks with augmented Lagrange multipliers},
  author={Stan Z. Li},
  journal={IEEE transactions on neural networks},
  year={1996},
  volume={7 6},
  pages={
          1507-16
        }
}
  • Stan Z. Li
  • Published in IEEE Trans. Neural Networks 1996
  • Medicine, Computer Science
  • Hopfield-type networks convert a combinatorial optimization to a constrained real optimization and solve the latter using the penalty method. There is a dilemma with such networks: when tuned to produce good-quality solutions, they can fail to converge to valid solutions; and when tuned to converge, they tend to give low-quality solutions. This paper proposes a new method, called the augmented Lagrange-Hopfield (ALH) method, to improve Hopfield-type neural networks in both the convergence and… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 49 CITATIONS

    A review on evolution of production scheduling with neural networks

    VIEW 7 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Structurally Incoherent Low-Rank 2DLPP for Image Classification

    VIEW 1 EXCERPT
    CITES METHODS

    CCN Energy-Delay Aware Cache Management Using Quantized Hopfield

    VIEW 1 EXCERPT
    CITES METHODS

    A Universal Concept Based on Cellular Neural Networks for Ultrafast and Flexible Solving of Differential Equations

    VIEW 1 EXCERPT
    CITES BACKGROUND

    An intelligent algorithm based on neural network for combinatorial optimization problems

    VIEW 1 EXCERPT
    CITES METHODS

    Stability of Coupled Local Minimizers Within the Lagrange Programming Network Framework

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 16 REFERENCES

    On the stability of the Travelling Salesman Problem algorithm of Hopfield and Tank

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Performance and fault-tolerance of neural networks for optimization

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    A New Method for Mapping Optimization Problems Onto Neural Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Alternative networks for solving the traveling salesman problem and the list-matching problem

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    An analogue approach to the travelling salesman problem using an elastic net method

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    `Neural' computation of decisions optimization problems

    • J. J. Hop eld, D. W. Tank
    • Biological Cybernetics,
    • 1985
    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Hop eld, \Neurons with graded response have collective computational properties like those of two state neurons

    • J J.
    • Proceedings of National Academic Science, USA,
    • 1984
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL