Sequential Monte Carlo Methods to Train Neural Network Models
We discuss a novel strategy for training neural networks using sequential Monte Carlo algorithms and propose a new hybrid gradient descent / sampling importance resampling algorithm (HySIR). In terms of computational time and accuracy, the hybrid SIR is a clear improvement over conventional sequenti...
Päätekijät: | Freitas, D, Nando, Niranjan, M, Gee, A, Doucet, A |
---|---|
Aineistotyyppi: | Journal article |
Julkaistu: |
2000
|
Samankaltaisia teoksia
-
Sequential monte carlo methods To train neural network models
Tekijä: , d, et al.
Julkaistu: (2000) -
Sequential Monte Carlo methods for diffusion processes
Tekijä: Jasra, A, et al.
Julkaistu: (2009) -
Sequential Monte Carlo samplers
Tekijä: Del Moral, P, et al.
Julkaistu: (2006) -
Sequential Monte Carlo for model selection and estimation of neural networks
Tekijä: Andrieu, C, et al.
Julkaistu: (2000) -
Controlled sequential Monte Carlo
Tekijä: Heng, J, et al.
Julkaistu: (2020)