Statistical Approximation Learning Method of Discontinuous Nonlinear Functions Using Simultaneous Recurrent Networks
Masao Sakai, Noriyasu Homma, Kenichi Abe · Transactions of the Society of Instrument and Control Engineers · 2003
In this paper, a statistical approximation learning (SAL) method is proposed for training a new type of neural networks which is known as simultaneous recurrent networks (SRNs). SRNs have the capability to approximate non-smooth functions which cannot be approximated by using conventional feedforward neural networks. However, most of learning methods for SRNs are computationally expensive due to their inherent recursive calculations. To solve this problem, a statistical relation between the time-series of the network outputs and the network configuration parameters is used in the proposed SAL method. Simulation results show that the SAL method can learn a strongly nonlinear function efficiently.