제어로봇시스템학회:학술대회논문집
- 1996.10b
- /
- Pages.1173-1176
- /
- 1996
A variance learning neural network for confidence estimation
신뢰도 추정을 위한 분산 학습 신경 회로망
Abstract
Multilayer feedforward networks may be applied to identify the deterministic relationship between input and output data. When the results from the network require a high level of assurance, considering of the stochastic relationship between the data may be very important. The variance is one of the useful parameters to represent the stochastic relationship. This paper presents a new algorithm for a multilayer feedforward network to learn the variance of dispersed data without preliminary calculation of variance. In this paper, the network with this learning algorithm is named as a variance learning neural network(VALEAN). Computer simulation examples are utilized for the demonstration and the evaluation of VALEAN.
Keywords
- stochastic process;
- gaussian distribution;
- variance learning;
- confidence estimation;
- multilayer feedforward network