Dynamics of fully complex-valued neural networks
@article{Hirose1992DynamicsOF, title={Dynamics of fully complex-valued neural networks}, author={A. Hirose}, journal={Electronics Letters}, year={1992}, volume={28}, pages={1492-1494} }
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.
Topics from this paper
121 Citations
An iterative learning scheme for multistate complex-valued and quaternionic Hopfield neural networks
- Computer Science
- 2009 International Joint Conference on Neural Networks
- 2009
- 17
Stability Analysis for Higher Order Complex-Valued Hopfield Neural Network
- Computer Science
- ICONIP
- 2006
- 7
On the fundamental properties of fully quaternionic hopfield network
- Mathematics, Computer Science
- The 2012 International Joint Conference on Neural Networks (IJCNN)
- 2012
- 16
- PDF
Some Properties of the Network Consisting of Two Complex-Valued Nagumo-Sato Neurons
- Computer Science
- KES
- 2003
- 1
Stability of Complex-Valued Neural Networks with Two Additive Time-Varying Delay Components
- Computer Science
- ISNN
- 2017
- 2
Qualitative Analysis of Continuous Complex-Valued Associative Memories
- Computer Science
- ICANN
- 2001
- 6
- Highly Influenced
Motion controls using complex-valued neural networks with feedback loops
- Computer Science
- IEEE International Conference on Neural Networks
- 1993
- 8
Proposal of relative-minimization learning for behavior stabilization of complex-valued recurrent neural networks
- Mathematics, Computer Science
- Neurocomputing
- 1999
- 10
Synchronization in Fractional-Order Complex-Valued Delayed Neural Networks
- Computer Science, Medicine
- Entropy
- 2018
- 14
- PDF
References
SHOWING 1-3 OF 3 REFERENCES
Neural networks and physical systems with emergent collective computational abilities.
- Computer Science, Medicine
- Proceedings of the National Academy of Sciences of the United States of America
- 1982
- 12,635
- PDF