Robust full Bayesian methods for neural networks
In this paper, we propose a full Bayesian model for neural networks. This model treats the model dimension (number of neurons), model parameters, regularisation parameters and noise parameters as random variables that need to be estimated. We then propose a reversible jump Markov chain Monte Carlo (...
Glavni autori: | Andrieu, C, de Freitas, J, Doucet, A |
---|---|
Format: | Conference item |
Izdano: |
Neural information processing systems foundation
2000
|
Slični predmeti
-
Robust Full Bayesian Learning for Radial Basis Networks
od: Andrieu, C, i dr.
Izdano: (2001) -
Robust full Bayesian learning for radial basis networks.
od: Andrieu, C, i dr.
Izdano: (2001) -
Sequential MCMC for Bayesian model selection
od: Andrieu, C, i dr.
Izdano: (1999) -
On sequential Monte Carlo sampling methods for Bayesian filtering
od: Doucet, A, i dr.
Izdano: (2000) -
Particle methods for Bayesian modeling and enhancement of speech signals
od: Vermaak, J, i dr.
Izdano: (2002)