Conference proceeding
Error estimation and error bounds for neural networks
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, pp 42-44
1995
Abstract
A method is proposed to estimate the standard error of predicted values in multilayer perceptron (MLP). It is based on likelihood theory. It holds for all feedforward networks, irrespective of the topology or the specific task at hand. In addition, the bounds on a neural network with perturbed weights and inputs is analytically derived. The bounds obtained are applicable to both digital and analog network implementations. By computer simulation, the validity of the proposed methods has been illustrated.
Metrics
9 Record Views
Details
- Title
- Error estimation and error bounds for neural networks
- Creators
- Hualou Liang - Comput. Center, Acad. Sinica, Beijing, ChinaGuiliang Dai - Comput. Center, Acad. Sinica, Beijing, China
- Publication Details
- Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, pp 42-44
- Publisher
- IEEE
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- School of Biomedical Engineering, Science, and Health Systems
- Scopus ID
- 2-s2.0-85063349405
- Other Identifier
- 991019320610204721