Please use this identifier to cite or link to this item:
Title: A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks
Authors: Xu, Zhao
Song, Qing
Wang, Danwei
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2013
Source: Xu, Z., Song, Q., & Wang, D. A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks. Neural Computing and Application,in press.
Series/Report no.: Neural computing and applications
Abstract: Training of recurrent neural networks (RNNs) introduces considerable computational complexities due to the need for gradient evaluations. How to get fast convergence speed and low computational complexity remains a challenging and open topic. Besides, the transient response of learning process of RNNs is a critical issue, especially for online applications. Conventional RNN training algorithms such as the backpropagation through time and real-time recurrent learning have not adequately satisfied these requirements because they often suffer from slow convergence speed. If a large learning rate is chosen to improve performance, the training process may become unstable in terms of weight divergence. In this paper, a novel training algorithm of RNN, named robust recurrent simultaneous perturbation stochastic approximation (RRSPSA), is developed with a specially designed recurrent hybrid adaptive parameter and adaptive learning rates. RRSPSA is a powerful novel twin-engine simultaneous perturbation stochastic approximation (SPSA) type of RNN training algorithm. It utilizes three specially designed adaptive parameters to maximize training speed for a recurrent training signal while exhibiting certain weight convergence properties with only two objective function measurements as the original SPSA algorithm. The RRSPSA is proved with guaranteed weight convergence and system stability in the sense of Lyapunov function. Computer simulations were carried out to demonstrate applicability of the theoretical results.
ISSN: 0941-0643
DOI: 10.1007/s00521-013-1436-5
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.