On the distributed parallel simulation of Hopfield's neural networks

Neural networks, or connectionist systems, have recently emerged as a powerful model of collective, parallel computation of great interest in artificial intelligence and combinatorial optimization. The understanding of neural networks is still largely dependent upon simulations, which in turn can be of great interest to the designer of parallel software, owing to the inherently distributed character of those systems. This paper is concerned with the simulation of one specific class of neural networks, namely those introduced by J. J. Hopfield. We discuss the design and occam implementation of a distributed parallel simulator of such networks, allowing for both binary- and continuous-response neurons. A design is provided which we judge to be generic to a large extent, and then problems related to an occam implementation are discussed. One problem of particular relevance is the potential occurrence of communication deadlocks as a result of the unbuffered communication among occam processes.