Three-state neural network: from mutual information to the Hamiltonian.

@article{Dominguez2000ThreestateNN,
  title={Three-state neural network: from mutual information to the Hamiltonian.},
  author={D. R. Carreta Dominguez and E. Korutcheva},
  journal={Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics},
  year={2000},
  volume={62 2 Pt B},
  pages={
          2620-8
        }
}
  • D. R. Carreta Dominguez, E. Korutcheva
  • Published 2000
  • Mathematics, Medicine, Physics, Biology, Computer Science
  • Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics
  • The mutual information, I, of the three-state neural network can be obtained exactly for the mean-field architecture, as a function of three macroscopic parameters: the overlap, the neural activity and the activity-overlap, i.e., the overlap restricted to the active neurons. We perform an expansion of I on the overlap and the activity-overlap, around their values for neurons almost independent of the patterns. From this expansion we obtain an expression for a Hamiltonian which optimizes the… CONTINUE READING
    21 Citations

    Figures and Topics from this paper

    Flow Diagrams of the Quadratic Neural Network
    • 6
    • PDF
    Information Processing and Energy Dissipation in Neurons
    • 1
    • PDF

    References

    SHOWING 1-10 OF 40 REFERENCES
    An introduction to the modeling of neural networks
    • 176
    Neural Network
    • 396
    • PDF
    Introduction to the theory of neural computation
    • 6,046
    • PDF
    A mathematical theory of communication
    • C. Shannon
    • Mathematics, Computer Science
    • Bell Syst. Tech. J.
    • 1948
    • 30,424
    • PDF
    Biological Cybernetics
    • 302
    Phys
    • 74, 565
    • 1994
    Physica A
    • Physica A
    • 1999
    Neural Network 2
    • 451
    • 1989
    Europhys
    • Lett. 4, 167
    • 1987
    Phys.Rev.A
    • Phys.Rev.A
    • 1971