Title :
Reliability modeling and design criteria for the backpropagation artificial neural network
Author_Institution :
Dept. of Reliability & Maintainability, McDonnell Aircraft Co., St. Louis, MO, USA
Abstract :
The author introduces a methodology which takes into account parametric behavior that contributes to reliable outputs. An approach to modeling the reliability of `reliable´ networks is developed. A major contributing point to the theory behind the model is that the weights connecting the hidden and output layers of the network must follow a normal distribution. This model is valid when and only when the normal distribution criterion is met. The model is applicable when a single connecting weight is set to 0 by component failure
Keywords :
backpropagation; circuit reliability; neural nets; backpropagation artificial neural network; design criteria; methodology; normal distribution; parametric behavior; reliability modeling; weights; Aircraft; Artificial neural networks; Backpropagation; Degradation; Equations; Lakes; Neural network hardware; Neural networks; Neurons; Predictive models;
Conference_Titel :
Reliability and Maintainability Symposium, 1993. Proceedings., Annual
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-0943-X
DOI :
10.1109/RAMS.1993.296868
