Method of parallel processing for inference and a system therefor

摘要

The same data is processed in parallel by a plurality of different algorithms for deriving the same processing result from the same data. When an algorithm derives a processing result first, the processing result is used and the processing by the other algorithms is stopped or interrupted and updated to the same data which is reflected by the processing result data. This updated data is processed in parallel once again by a plurality of different algorithms, and when an algorithm derives another processing result first, the processing result is used, and the above processing is repeated, and inference. Consequently, sorting, data compression, simulation, and neurolearning can be processed at the highest possible speed.