Neural network simulation on a reduced-mesh-of-trees organization
Manavendra Misra, V. Krishna Kumar · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1990
The theory of Artificial Neural Networks (ANN's) shows that ANN's can perform useful image recognition functions. Simulations on uniprocessor sequential machines, however, destroy the parallelism inherent in ANN models and this results in a significant loss of speed. Simulations on parallel machines are therefore essential to fully exploit the advantages of ANN's. We show how to simulate ANN's on an SIMD architecture, the Reduced Mesh of Trees (RMOT). The architecture has p PE's and n2 memory arranged in a p x p array of modules (p is a constant less than or equal to n). This massive memory is used to store connection weights. A fully connected, single layer neural network with n neurons can be mapped easily onto the architecture. An update in this case requires O(n2/p) time steps. A sparse network can also be simulated efficiently on the architecture. The proposed architecture can also be used for the efficient simulation of multilayer networks with a Back Propagation learning scheme. The architecture can easily be implemented within the framework of existing hardware technology.