A class of instantaneously trained neural networks
This paper presents FC networks which are instantaneously trained neural networks that allow rapid learning of non-binary data. These networks, which generalize the earlier corner classification (CC) networks, have been compared against Backpropagation (BP) and Radial Basis Function (RBF) networks a...
Saved in:
Published in | Information sciences Vol. 148; no. 1; pp. 97 - 102 |
---|---|
Main Author | |
Format | Journal Article |
Language | English |
Published |
Elsevier Inc
01.12.2002
|
Online Access | Get full text |
Cover
Loading…
Summary: | This paper presents FC networks which are instantaneously trained neural networks that allow rapid learning of non-binary data. These networks, which generalize the earlier corner classification (CC) networks, have been compared against Backpropagation (BP) and Radial Basis Function (RBF) networks and are seen to have excellent performance for prediction of time-series and pattern recognition. The networks can generalize using soft or hard decisions. |
---|---|
ISSN: | 0020-0255 1872-6291 |
DOI: | 10.1016/S0020-0255(02)00281-5 |