Neural networks on a transputer array

The problem of the efficient simulation of neural networks on parallel machines is addressed. First, the computationally most efficient neural algorithms capturing the functionality of the network are searched for. Then their implementations on a given concurrent machine (a transputer array programmed in Occam) is presented and discussed. Single-layer networks, described by the additive, or Hopfield, model are considered. Results of the solution of optimization problems (analog/digital conversion and the traveling salesman problem) are given