High performance fault-tolerant digital neural networks

Efficient implementation of neural networks requires high-performance architectures, while VLSI realization for mission-critical applications must include fault tolerance. Contemporaneous solution of such problems has not yet been completely afforded in the literature. This paper focuses both on data representation to support high-performance neural computation and on error detection to provide the basic information for fault tolerance by using the redundant binary representation with a three-rail logic implementation. Costs and performances are evaluated referring to multilayered feed-forward networks.