May be of use but very heavy maths will have to review better but matches my check-list well , has my exact keywords but will look at different Neural Nets and see what one will be the best for me.
Abstract:
MacKay's (1992) Bayesian framework for backpropagation is a practical and powerful means to improve the generalization ability of neural networks. It is based on a Gaussian approximation to the posterior weight distribution. The framework is extended, reviewed, and demonstrated in a pedagogical way. The notation is simplified using the ordinary weight decay parameter, and a detailed and explicit procedure for adjusting several weight decay parameters is given. Bayesian backprop is applied in the prediction of fat content in minced meat from near infrared spectra. It outperforms “early stopping” as well as quadratic regression. The evidence of a committee of differently trained networks is computed, and the corresponding improved generalization is verified. The error bars on the predictions of the fat content are computed. There are three contributors: The random noise, the uncertainty in the weights, and the deviation among the committee members. The Bayesian framework is compared to Moody's GPE (1992). Finally, MacKay and Neal's automatic relevance determination, in which the weight decay parameters depend on the input number, is applied to the data with improved results
Date of Publication: Jan 1996
- Page(s):
- 56 - 72
- ISSN :
- 1045-9227
- INSPEC Accession Number:
- 5181044
- Digital Object Identifier :
- 10.1109/72.478392
- Date of Current Version :
- 06 August 2002
- Issue Date :
- Jan 1996
- Sponsored by :
- IEEE Computational Intelligence Society
No comments:
Post a Comment