On Verification & Validation of Neural Network Based Controllers

Artificial neural networks (ANNs) are used as an alternative to traditional models in the realm of control. Unfortunately, ANN models rarely provide any indication of accuracy or reliability of their predictions. Before ANNs can be used in safety critical applications (aircraft, nuclear plants, etc.), a certification process must be established for ANN based controllers. Traditional approaches to validation of neural networks are mostly based on empirical evaluation through simulation and/or experimental testing. For on-line trained ANNs used in safety critical applications, traditional methods of verification and validation cannot be applied, leaving a wide technological gap, which we attempt to address in this paper. We will describe a layered approach for ANN V&V which includes a V&V software process for pre-trained neural networks, a detailed discussion of numerical issues, and techniques for dynamically measuring and monitoring the confidence of the ANN output.