Neural metrics-software metrics in artificial neural networks
W. K. Leung, Robert Simpson · 2002
Backpropagation based supervised feedforward artificial neural networks (ANNs) have been developed for many applications (e.g. Rumelhart et al., 1986; Hinton, 1989; Werbos, 1990; and Riedmiller, 1994) but no detailed study of the measurement of the quality characteristics (e.g complexity and efficiency) of the network system has been made. Without an appropriate measurement, it is difficult to tell how the network performs on given applications. In addition, it is difficult to provide a measure of the algorithmic complexity of any given application. The paper proposes a new set of software metrics, named neural metrics, which provide indicative measures of the quality characteristics of ANNs. Neural metrics that are non-primitive in nature are defined mathematically as neural metrics functions.