. Agency Use Only(leave Blank) 2. Report Date 3. Report Type and Dates Covered Fault Tolerance of Artiicial Neural Networks with Applications in Critical Systems

One of the key bene ts of future hardware implementations of certain arti cial neural networks (ANN's) is their apparently \built-in" fault tolerance which makes them potential candidates for critical tasks with high reliability requirements. This paper investigates the fault-tolerance characteristics of time-continuous, recurrent ANN's that can be used to solve optimization problems. The principle of operation and the performance of these networks are rst illustrated by using well-known model problems like the traveling salesman problem and the assignment problem. The ANN's are then subjected to up to 13 simultaneous \stuckat-1" or \stuck-at-0" faults for network sizes of up to 900 \neurons." The e ect of these faults on the performance is demonstrated and the cause for the observed fault tolerance is discussed. An application is presented in which a network performs a critical task for a realtime distributed processing system by generating new task allocations during the recon guration of the system. The performance degradation of the ANN under the presence of faults is investigated by large-scale simulations, and the potential bene ts of delegating a critical task to a fault-tolerant network are discussed.