Back to Search
Start Over
AN ADAPTIVE MODULAR NEURAL NETWORK WITH APPLICATION TO UNCONSTRAINED CHARACTER RECOGNITION.
- Source :
- International Journal of Pattern Recognition & Artificial Intelligence; Oct1994, Vol. 8 Issue 5, p1189-1204, 16p
- Publication Year :
- 1994
-
Abstract
- The topology and the capacity of a traditional multilayer neural system, as measured by the number of connections in the network, has surprisingly little impact on its generalization ability. This paper presents a new adaptive modular network that offers superior generalization capability. The new network provides significant fault tolerance, quick adaption to novel inputs, and high recognition accuracy. We demonstrate this paradigm on recognition of unconstrained handwritten characters. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 02180014
- Volume :
- 8
- Issue :
- 5
- Database :
- Complementary Index
- Journal :
- International Journal of Pattern Recognition & Artificial Intelligence
- Publication Type :
- Academic Journal
- Accession number :
- 126673714
- Full Text :
- https://doi.org/10.1142/S0218001494000590