Rapid training of GIL neural networks
Clark D. Jeffries, Peter C. Kiessler, Louis N. Ntasin · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1999
Applying generalized inverse learning to a feedforward neural network has been shown to be an effective tool in pattern recognition. The difficult computational step is finding the pseudo-inverse of a matrix. In this paper, we develop an efficient method using differential equations to calculate the pseudo-inverse.