Fast linear system solution by neural networks

The authors present a highly parallel model for solving the m×n linear system Ax=b, based on the connectionist paradigm of neural networks. Using m+n linear, perceptron-like neurons, the neutral model converges fast to a problem solution, when one exists, or to a least-squares approximation, when the problem is inconsistent. The velocity of convergence of an analog realization of the network does not depend on m or n, but rather on the eigenvalues of A^TA. Simulation results in linear system solution and suggestions for applications are given.