Statistical learning method of discontinuous functions using simultaneous recurrent networks
Masao Sakai, Noriyasu Homma, K. Abe · 2003
A statistical approximation learning (SAL) method is proposed for a new type of neural network: simultaneous recurrent networks (SRNs). SRNs have the ability to approximate non-smooth functions which cannot be approximated by using conventional multi-layer perceptrons (MLPs). However, most of the learning methods for SRNs are computationally expensive due to their inherent recursive calculations. To solve this problem, a novel approximation learning method is proposed by using a statistical relation between the time series of the network outputs and the network configuration parameters. Simulation results show that the proposed method can learn a strongly nonlinear function efficiently.