Parallel digital implementations of neural networks
K. Wojtek Przytula · 2002
The paper reviews implementations of neural networks on parallel digital machines. The connectionist neural networks models are discussed from the point of view of their computational characteristics. The levels of parallelism available in the models and the factors affecting their performance of the models on the parallel machines are presented. Several mapping methodologies applicable to neural networks are described. Selected examples of implementations of neural networks on parallel digital machines are provided.>