Continuous complex-valued back-propagation learning

@article{Hirose1992ContinuousCB,
  title={Continuous complex-valued back-propagation learning},
  author={A. Hirose},
  journal={Electronics Letters},
  year={1992},
  volume={28},
  pages={1854-1855}
}
  • A. Hirose
  • Published 1992
  • Computer Science
  • Electronics Letters
  • A novel back-propagation learning method is proposed for fully complex-valued layered neural networks. Nonlinearity suitable for realising smooth and unified complex learning is introduced. A gradient descent method is also analysed and optimised so that the variations of independent elements of the output complex vectors are related directly to the fragmentary changes of weighting matrix elements. The learning process is presented and demonstrated. 
    89 Citations

    Topics from this paper

    Learning Scheme for Complex Neural Networks Using Simultaneous Perturbation
    • 1
    Fully Complex Multi-Layer Perceptron Network for Nonlinear Signal Processing
    • 156
    Phase-based neuron training using evolutionary algorithms
    Quaternionic Multilayer Perceptron with Local Analyticity
    • 34
    A Complex-Valued RTRL Algorithm for Recurrent Neural Networks
    • 83
    • PDF
    Historical Consistent Complex Valued Recurrent Neural Network
    • 9
    • PDF
    Valued Neural Networks
    • PDF
    Is a Complex-Valued Stepsize Advantageous in Complex-Valued Gradient Learning Algorithms?
    • H. Zhang, D. Mandic
    • Mathematics, Medicine
    • IEEE Transactions on Neural Networks and Learning Systems
    • 2016
    • 17
    • Highly Influenced
    • PDF

    References

    SHOWING 1-4 OF 4 REFERENCES
    Proposal of fully complex-valued neural networks
    • A. Hirose
    • Mathematics
    • [Proceedings 1992] IJCNN International Joint Conference on Neural Networks
    • 1992
    • 37
    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
    • 12,642
    • PDF
    Statistical neurodynamics of associative memory
    • 378
    Self-Organization and Associative Memory
    • 5,913