Power curves for pattern classification networks

The authors discuss the development of a methodology for evaluating and predicting the goodness of a pattern classification neural network based on the statistical concept of power. Power is the ability of a statistical test to detect a phenomenon when it exists. An artificial neural network (ANN) analogy to the statistical concept of power is examined. Several experiments are presented to empirically support parallels drawn between the power of a statistic and the power of ANN trained on a 2-class pattern classification problem. The utility of power as a general neural network concept is discussed.<>