Bayesian methods for neural networks

By Gomes de Freitas, João Ferdinando. 2000

128 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Scalable Bayesian Optimization Using Deep Neural Networks (2015, methodology): “…methods to neural networks has a rich history in machine learning (MacKay, 1992; Hinton & van Camp, 1993; Buntine & Weigend, 1991; Neal, 1995; De Freitas, 2003) and Mnih & Gregor (2014), where a neural network is used in a variational approximation to the posterior distribution over the latent…”
Deep learning in neural networks: An overview (2014, background): “…the MDL principle suggests that low NN weight complexity corresponds to high NN probability in the Bayesian view (e.g., Buntine & Weigend, 1991; De Freitas, 2003; MacKay, 1992; Neal, 1995), and to high generalization performance (e.g., Baum & Haussler, 1989), without overfitting the training…”
Expectation propagation for neural networks with sparsity-promoting priors (2013, methodology): “Previously, Gaussian approximations for NN models have been formed using the extended Kalman filter (EKF) (de Freitas, 1999) and the unscented Kalman filter (UKF) (Wan and van der Merwe, 2000). Alternative mean field approaches possessing similar characteristic with EP have been proposed by Opper an”
Sequential Monte Carlo methods for multiple target tracking and data fusion (2002, methodology): “See [7] for an introduction to MCMC simulation methods and also for a presentation of the EM algorithm.”
Nonparametric Neural Networks (2017, unknown): “Bayesian neural networks (e.g. McKay (1992), De Freitas (2003)) use a probabilistic prior instead of a regularizer to control the complexity of the network.”
Bayesian Neural Networks for Internet Traffic Classification (2007, methodology): “See [31] and references therein for background, and a Bayesian treatmen t is provided in [32].”
Sigma-point kalman filters for probabilistic inference in dynamic state-space models (2004, background): “While still making a Gaussian assumption, the approach provides a better approximation to the optimal conditional proposal distribution and has been shown to improve performance on a number of applications [5].”
Rao-Blackwellised Particle Filtering for Dynamic Bayesian Networks (2000, methodology): “Several deterministic approximations to the optimal distribution have been proposed , see for example (de Freitas 1999, Doucet 1998).”
MOrdReD: Memory-based Ordinal Regression Deep Neural Networks for Time Series Forecasting (2018, background): “Machine Learning (ML) has a rich history in the time series literature, covering a broad range of methods such as random forest regressors [2], quantile random forests [3] and artiﬁcial neural networks (ANNs) [4].”