The morphological shared-weight neural network (MSNN) is an effective approach to automatic target recognition. Implementation of the network in parallel is critical for real-time target recognition systems. Although ...
详细信息
ISBN:
(纸本)0819429074
The morphological shared-weight neural network (MSNN) is an effective approach to automatic target recognition. Implementation of the network in parallel is critical for real-time target recognition systems. Although there is significant parallelism inherent in the MSNN, it is a challenge to implement it on an simd parallel computer consisting of a large array of simple processing elements. This paper discusses issues related to detection accuracy and throughput in implementing the MSNN on the Parallel Algebraic Logic (PAL) computer.
Benchmarking an simd pyramid with the Abingdon Cross is discussed. Measured results for a simulated pyramid architecture on a CLIP4 processorarray are presented, as well as estimates for a hypothetical hardware pyram...
详细信息
Benchmarking an simd pyramid with the Abingdon Cross is discussed. Measured results for a simulated pyramid architecture on a CLIP4 processorarray are presented, as well as estimates for a hypothetical hardware pyramid built with CLIP4 like processing elements.
暂无评论