Dynamics of fully complex-valued neural networks

  title={Dynamics of fully complex-valued neural networks},
  author={A. Hirose},
  journal={Electronics Letters},
  • A. Hirose
  • Published 1992
  • Computer Science
  • Electronics Letters
  • A novel neural network that processes input vectors and attractors fully in complex space using complex weights is proposed. Real and imaginary data are treated consistently with an equivalent significance in nondegenerate complex space. This network can be applied for ill-posed problems concerning realistic physical fields and continuous motion controls. The dynamics are presented and demonstrated. 
    121 Citations

    Topics from this paper

    An iterative learning scheme for multistate complex-valued and quaternionic Hopfield neural networks
    • 17
    Valued Neural Networks
    • PDF
    On the fundamental properties of fully quaternionic hopfield network
    • 16
    • PDF
    Some Properties of the Network Consisting of Two Complex-Valued Nagumo-Sato Neurons
    • 1
    Qualitative Analysis of Continuous Complex-Valued Associative Memories
    • 6
    • Highly Influenced
    Motion controls using complex-valued neural networks with feedback loops
    • A. Hirose
    • Computer Science
    • IEEE International Conference on Neural Networks
    • 1993
    • 8
    Proposal of relative-minimization learning for behavior stabilization of complex-valued recurrent neural networks
    • 10
    Synchronization in Fractional-Order Complex-Valued Delayed Neural Networks
    • 14
    • PDF


    Statistical neurodynamics of associative memory
    • 377
    Neural networks and physical systems with emergent collective computational abilities.
    • J. Hopfield
    • Computer Science, Medicine
    • Proceedings of the National Academy of Sciences of the United States of America
    • 1982
    • 12,635
    • PDF
    Self-Organization and Associative Memory
    • 5,911