Multicomputer-based Neural Networks for Imaging in Random Media

F.H. Schlereth et al. (1991)


In this paper we describe a new technique for imaging in random media using a neural network approach based on a modified backpropagation algorithm. Simulation results indicate that we are able to produce images of simple structures in 2-D media with a reasonable computation time. Our approach is computation intensive and for this reason we have developed a machine architecture and machine, Kilonode, which is well suited to this class of computing problems, and which can ultimately be produced at a cost which is suitable for commercial application of the neural network algorithms.