The Community for Technology Leaders
Green Image
<p>Reprogrammable dataflow neural classifiers are proposed as an alternative to traditional implementations. In general, these classifiers are based on functional languages, neural-dataflow transformations, dataflow algorithmic transformations, and dataflow multiprocessors. An experimental approach is used to investigate the performance of a large-scale fine-grained dataflow classifier architecture. In this study, the functional descriptions of high level data dependency of a supervised learning algorithm are transformed into a machine executable low-level dataflow graph. The tagged token dataflow algorithmic transformation is applied to exploit the parallelism. Dataflow neural classifiers are used to implement the learning algorithm. No attempt is made to optimize the granularity of the high-level language programming blocks to balance the computation and communication. The proposed classifier architecture is more versatile than other existing architectures. Performance results show the effectiveness of dataflow neural classifiers.</p>
algorithmic transformations; reprogrammable dataflow neural classifiers; neural computing; performance; supervised learning; dataflow machine; functional languages; neural-dataflow transformations; dataflow algorithmic transformations; dataflow multiprocessors; high level data dependency; machine executable low-level dataflow graph; tagged token dataflow algorithmic transformation; granularity; computerized pattern recognition; learning systems; neural nets; parallel architectures; performance evaluation

S. Kim, J. Herath, A. Jayasumana, K. Suwunboriruksa and S. Herath, "Algorithmic Transformations for Neural Computing and Performance of Supervised Learning on a Dataflow Machine," in IEEE Transactions on Software Engineering, vol. 18, no. , pp. 613-623, 1992.
93 ms
(Ver 3.3 (11022016))