Simultaneous Perturbation Learning Rule for Recurrent Neural Networks and Its FPGA Implementation
- 7 November 2005
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 16 (6) , 1664-1672
- https://doi.org/10.1109/tnn.2005.852237
Abstract
Recurrent neural networks have interesting properties and can handle dynamic information processing unlike ordinary feedforward neural networks. However, they are generally difficult to use because there is no convenient learning scheme. In this paper, a recursive learning scheme for recurrent neural networks using the simultaneous perturbation method is described. The detailed procedure of the scheme for recurrent neural networks is explained. Unlike ordinary correlation learning, this method is applicable to analog learning and the learning of oscillatory solutions of recurrent neural networks. Moreover, as a typical example of recurrent neural networks, we consider the hardware implementation of Hopfield neural networks using a field-programmable gate array (FPGA). The details of the implementation are described. Two examples of a Hopfield neural network system for analog and oscillatory targets are shown. These results show that the learning scheme proposed here is feasible.Keywords
This publication has 20 references indexed in Scilit:
- Scalable Closed-Boundary Analog Neural NetworksIEEE Transactions on Neural Networks, 2004
- Analog and digital fpga implementation of brin for optimization problemsIEEE Transactions on Neural Networks, 2003
- Implementation issues of neuro-fuzzy hardware: going toward HW/SW codesignIEEE Transactions on Neural Networks, 2003
- Hardware Implementation of a Pulse Density Neural Network Using Simultaneous Perturbation Learning RuleAnalog Integrated Circuits and Signal Processing, 1999
- Learning rules for neuro-controller via simultaneous perturbationIEEE Transactions on Neural Networks, 1997
- An analog VLSI recurrent neural network learning a continuous-time trajectoryIEEE Transactions on Neural Networks, 1996
- A learning rule of neural networks via simultaneous perturbation and its hardware implementationNeural Networks, 1995
- Neural Information Processing and VLSIPublished by Springer Nature ,1995
- A generic systolic array building block for neural networks with on-chip learningIEEE Transactions on Neural Networks, 1993
- Multivariate stochastic approximation using a simultaneous perturbation gradient approximationIEEE Transactions on Automatic Control, 1992