Experimental Investigation of the Fault Tolerance of IDS Models

Abstract

The ink drop spread (IDS) method is a modeling technique that is proposed as a new paradigm of soft computing. The structure of IDS models is similar to that of artificial neural networks (ANNs): they comprise distributed processing units. The beneficial property of fault tolerance is obtained when such parallel processing networks are implemented with dedicated hardware. Among the ANNs, radial basis function networks (RBFNs) are known to possess superior fault tolerance. This study evaluates the fault tolerances of the IDS models and RBFNs using the approximation of continuous functions. The experimental results demonstrate that the IDS models are highly fault tolerant in comparison with the RBFNs.