DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Young B. | - |
dc.contributor.author | Gweon, D. G. | - |
dc.date.accessioned | 2011-07-04T07:33:51Z | - |
dc.date.available | 2011-07-04T07:33:51Z | - |
dc.date.issued | 1997-06 | - |
dc.identifier.citation | Journal of the Korean Society for Precision Engineering, Vol.14, No.6 | en |
dc.identifier.uri | http://hdl.handle.net/10203/24399 | - |
dc.description.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, comsideration of the stochastic relationship between the input and output data may be very important.Variance is one of the effective parameters to deal with 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 veriance learning neural network. Computer simulation examples are utilized for the demonstration and the evaluation of VANEAN. | en |
dc.language.iso | ko | en |
dc.publisher | Korean Society for Precision Engineering | en |
dc.subject | 확률과정 | en |
dc.subject | 가우시안 분포 | en |
dc.subject | 분산학습 | en |
dc.subject | 신뢰도추정 | en |
dc.subject | 다층신경회로망 | en |
dc.subject | 다층퍼셉트론 | en |
dc.title | 신뢰도 추정을 위한 분산 학습 신경 회로망 | en |
dc.title.alternative | A variance Learning Neural Network for Confidence Estimation | en |
dc.type | Article | en |
dc.subject.alternative | Stochastic Process | en |
dc.subject.alternative | Gaussian Distribution | en |
dc.subject.alternative | Variance Learning | en |
dc.subject.alternative | Confidence Estimation | en |
dc.subject.alternative | Multilayer Perceptron | en |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.