Learning scheme for complex neural networks using simultaneous perturbation
作者： Yutaka Maeda , Takahiro Yamada , Seiji Miyoshi , Hiroomi Hikawa
DOI: 10.1007/978-3-642-21738-8_59
关键词:
摘要: Usually, the back-propagation learning rule is widely used for complex-valued neural networks as well. On other hand, in this paper, using simultaneous perturbation optimization method proposed. Comparison between and made some test problems. Simplicity of proposed results faster speed.
springer.com
sci-hub.st 参考文章(16)
Yutaka Maeda, Yakichi Kanata, Learning Rules for Recurrent Neural Networks using Perturbation and their Application to Neuro-Control Ieej Transactions on Electronics, Information and Systems. ,vol. 113, pp. 402- 408 ,(1993) , 10.1541/IEEJEISS1987.113.6_402
Yutaka Maeda, Yakichi Kanata, A Learning Rule of Neural Networks for Neuro-controller 関西大学工業技術研究所研究報告. ,vol. 15, pp. 403- 406 ,(2000)
Yutaka Maeda, Atsushi Nakazawa, Yakichi Kanata, Hardware Implementation of a Pulse Density Neural Network Using Simultaneous Perturbation Learning Rule Analog Integrated Circuits and Signal Processing. ,vol. 18, pp. 153- 162 ,(1999) , 10.1023/A:1008355204358
A. Hirose, Continuous complex-valued back-propagation learning Electronics Letters. ,vol. 28, pp. 1854- 1855 ,(1992) , 10.1049/EL:19921186
G. Cauwenberghs, An analog VLSI recurrent neural network learning a continuous-time trajectory IEEE Transactions on Neural Networks. ,vol. 7, pp. 346- 361 ,(1996) , 10.1109/72.485671
Akira Hirose, Complex-Valued Neural Networks ,(2006)
James C. Spall, A Stochastic Approximation Technique for Generating Maximum Likelihood Parameter Estimates american control conference. pp. 1161- 1167 ,(1987) , 10.1109/ACC.1987.4172518
Y. Maeda, R.J.P. De Figueiredo, Learning rules for neuro-controller via simultaneous perturbation IEEE Transactions on Neural Networks. ,vol. 8, pp. 1119- 1130 ,(1997) , 10.1109/72.623213
A. Hirose, Dynamics of fully complex-valued neural networks Electronics Letters. ,vol. 28, pp. 1492- 1494 ,(1992) , 10.1049/EL:19920948
Y. Maeda, T. Tada, FPGA implementation of a pulse density neural network with learning ability using simultaneous perturbation IEEE Transactions on Neural Networks. ,vol. 14, pp. 688- 695 ,(2003) , 10.1109/TNN.2003.811357