A graphical tool for implementing Neural Networks for digital Signal Processing on Parallel computers
An emerging and rapidly expanding Parallel Distributed Processing technology for Signal Processing is the Neural Network. Artificial Neural Networks (ANNs) have been effectively used in the solution of signal processing problems, such as optimisation, identification and prediction. A graphical entry tool, SoftDSP, designed for the simulation of DSP functions, has been used as a front end for a graphical compiler to develop ANNs for parallel systems. The compiled code is implemented in parallel C which can be mapped onto an array of transputers.