JackKnife method for validating neural network models

Summary form only given. Most methods for validating neural networks rely on the exclusion of a portion of the data throughout a portion or all of the network training process. This approach can be somewhat wasteful, particularly when the cost of samples can exceed a million dollars each. It is suggested that a more appropriate (and efficient) validation method is the JackKnife method. Although the JackKnife method was developed to validate statistical estimation procedures, it is equally applicable to the process of validating the performance of a neural network.<
>