Systolic array algorithm for the Hopfield neural network guaranteeing convergence

It has been frequently reported that the Hopfield neural network operating in discrete-time and parallel update mode will not converge to a stable state, which inhibits the parallel execution of the model. The authors propose a systolic array algorithm for the parallel simulation of the Hopfield neural network which guarantees the convergence of the network and achieves linear speedup as the number of processors is increased.