Recognition of handwritten digits using a neural network based on the piecewise linear function
Hongyu Liu, Yialei Wang, Peimao Sun, Tianyun Zhang, Rong Jiang · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1994
In this paper, a practical method for building and training a neural network to recognize handwritten digits is presented. The learning speed of this algorithm is remarkably fast compared with that of the back-propagation algorithm. It also provides the network with the ability to adjust its configuration according to the complexity of a given problem. An optoelectronic setup is devised to implement this algorithm.