A test methodology for artificial neural networks

This paper continues developments of a new and novel testing approach for detecting interconnection deletion faults in electronic implementations of artificial neural networks (ANNs). The testing approach is based on an unusual ANN behavior manifested by faulted ANNs having apparent better performance than fault-free ANNs, when neurons are operated with low activation function gains. Although transient, this noncoherent behavior can be used to detect interconnection deletion faults in ANNs. A hardware implementation of the digital aspects of the test circuitry is presented, suggesting the testing methodology may be suitable for built-in test. Simulation models of the proposed test circuitry have been verified and the implications of the testing methodology are discussed