Bayesian approach for neural networks--review and case studies

By Jouko Lampinen, Aki Vehtari. 2001

417 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering

How researchers see this paper

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

In Artificial Intelligence

In Control and Systems Engineering

Citations in the corpus

Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors (2018, background): “Priors for neural networks Classic work has investigated entropic priors (Buntine and Weigend, 1991) and hierarchical priors (MacKay, 1992b; Neal, 2012; Lampinen and Vehtari, 2001 2018)), NCPs take the functional view by imposing explicit regularities in terms of the network’s inputs and outputs.”
Expectation propagation for neural networks with sparsity-promoting priors (2013, methodology): “The second case study illustrates the effects of sparse priors using a similar regression example as considered by Lampinen and Vehtari (2001).”
An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models (2002, methodology): “MCMC techniques have been successfully applied to practical supervised learning problems, for example in (Lampinen and Vehtari, 2001) by using a MLP network structure.”
MCMC Methods for MLP-network and Gaussian Process and Stuff – A documentation for Matlab Toolbox (2006, methodology): “In linear models these weights define the partial derivatives of the output with respect to the inputs, which is equal to the predictive importance of the input (Lampinen and Vehtari, 2001), in the case of nonlinear MLP network the situation is, however, more complicated.”
Classification with Bayesian Neural Networks (2005, background): “Lampinen and Vehtari (2001) provide a more recent review and case studies.”
Noise Contrastive Priors for Functional Uncertainty (2018, background): “Priors for neural networks Classic work has investigated entropic priors (Buntine and Weigend, 1991) and hierarchical priors (MacKay, 1992b; Neal, 2012; Lampinen and Vehtari, 2001).”
Future research challenges for incorporation of uncertainty in environmental and ecological decision-making (2008, methodology): “Methods such as those discussed in Lampinen and Vehtari (2001) and Kingston et al. (2005) go partway towards addressing this problem by enabling metamodel parameter uncertainty to be taken into account explicitly.”
Global crustal thickness from neural network inversion of surface wave data (2007, background): “…(1996) for example used a neural network to predict fat content in minced meat from near infrared spectra, Cornford et al. (1999) retrieved wind vectors from satellite scatterometer data, and Lampinen & Vehtari (2001) investigated the use of neural networks in electrical impedance tomography.”
Bio inspired computing - A review of algorithms and scope of applications (2016, methodology): “Neural networks (Fausett, 1994; Craven & Shavlik, 1997; Lampinen & Vehtari, 2001) have been used extensively for generation of association rules, classification problems, detection problems, pattern recognition, non-linear regression, feature selection, missing data prediction, time-series…”
Hands-On Bayesian Neural Networks—A Tutorial for Deep Learning Users (2020, background): “There is a rich literature in the field of Bayesian (deep) learning, including reviews [50, 85, 89], but none of which explores, in a specific and exhaustive way, the general theory of Bayesian neural networks.”
A review on lithium-ion battery ageing mechanisms and estimations for automotive applications (2013, methodology): “NN performs despite multi-dependences and a rms the easy adaptivity of the method to other battery technology [141].”