Share Email Print
cover

Proceedings Paper

Recognition of handwritten digits using a neural network based on the piecewise linear function
Author(s): Hongyu Liu; Yialei Wang; Peimao Sun; Tianyun Zhang; Rong Jiang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper 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.

Paper Details

Date Published: 5 August 1994
PDF: 3 pages
Proc. SPIE 2321, Second International Conference on Optoelectronic Science and Engineering '94, (5 August 1994); doi: 10.1117/12.182096
Show Author Affiliations
Hongyu Liu, Tsinghua Univ. (China)
Yialei Wang, Tsinghua Univ. (China)
Peimao Sun, Tsinghua Univ. (China)
Tianyun Zhang, Tsinghua Univ. (China)
Rong Jiang, Tsinghua Univ. (China)


Published in SPIE Proceedings Vol. 2321:
Second International Conference on Optoelectronic Science and Engineering '94
Wang Da-Heng; Anna Consortini; James B. Breckinridge, Editor(s)

© SPIE. Terms of Use
Back to Top