Learning scheme for complex neural networks using simultaneous perturbation

Authors:
Yutaka Maeda;Takahiro Yamada;Seiji Miyoshi;Hiroomi Hikawa
Affiliations:
Kansai University, Faculty of Engineering Science, Suita, Japan;Kansai University, Faculty of Engineering Science, Suita, Japan;Kansai University, Faculty of Engineering Science, Suita, Japan;Kansai University, Faculty of Engineering Science, Suita, Japan
Venue:
ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
Year:
2011

Citing 9
Cited 1

A learning rule of neural networks via simultaneous perturbation and its hardware implementation

Neural Networks
An extension of the back-propagation algorithm to complex numbers

Neural Networks
Hardware Implementation of a Pulse Density Neural Network Using Simultaneous Perturbation Learning Rule

Analog Integrated Circuits and Signal Processing - Special issue on Learning on Silicon
Complex-valued Neural Networks: Utilizing High-dimensional Parameters

Complex-valued Neural Networks: Utilizing High-dimensional Parameters
An analog VLSI recurrent neural network learning a continuous-time trajectory

IEEE Transactions on Neural Networks
Complex-valued multistate neural associative memory

IEEE Transactions on Neural Networks
Learning rules for neuro-controller via simultaneous perturbation

IEEE Transactions on Neural Networks
FPGA implementation of a pulse density neural network with learning ability using simultaneous perturbation

IEEE Transactions on Neural Networks
Simultaneous perturbation learning rule for recurrent neural networks and its FPGA implementation

IEEE Transactions on Neural Networks

Complex-valued neural network using simultaneous perturbation with dynamic tunneling technique

Proceedings of the Second International Conference on Computational Science, Engineering and Information Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Usually, the back-propagation learning rule is widely used for complex-valued neural networks as well. On the other hand, in this paper, learning rule for complex-valued neural networks using the simultaneous perturbation optimization method is proposed. Comparison between the back-propagation method and the proposed. simultaneous perturbation learning rule is made for some test problems. Simplicity of the proposed method results in faster learning speed.