5 August 1994 Recognition of handwritten digits using a neural network based on the piecewise linear function
Author Affiliations +
Proceedings Volume 2321, Second International Conference on Optoelectronic Science and Engineering '94; (1994) https://doi.org/10.1117/12.182096
Event: Optoelectronic Science and Engineering '94: International Conference, 1994, Beijing, China
Abstract
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.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hongyu Liu, Hongyu Liu, Yialei Wang, Yialei Wang, Peimao Sun, Peimao Sun, Tianyun Zhang, Tianyun Zhang, Rong Jiang, Rong Jiang, } "Recognition of handwritten digits using a neural network based on the piecewise linear function", Proc. SPIE 2321, Second International Conference on Optoelectronic Science and Engineering '94, (5 August 1994); doi: 10.1117/12.182096; https://doi.org/10.1117/12.182096
PROCEEDINGS
3 PAGES


SHARE
Back to Top