Issues in Bayesian Analysis of Neural Network Models

By Peter Müller, David Ríos Insua. 1998

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

Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors (2018, background): “For example, neural network models are non-identifiable due to weight symmetries that can produce the same function output (Müller and Insua, 1998).”
Support Vector Machines with Applications (2006, background): “On the other hand, neural network parameters are very hard to tune and interpret, and statistical inference is usually not possible [51].”
Noise Contrastive Priors for Functional Uncertainty (2018, background): “For example, neural network models are non-identifiable due to weight symmetries that yield the same function (Müller and Insua, 1998).”
Neural networks for classification: a survey (2000, background): “size issues [51], [135], [136], Bayesian analysis [102], [109], [110], [120], and wavelet networks [165], [166], [196].”
Reconciling meta-learning and continual learning with online mixtures of tasks (2018, methodology): “However, in the setting of latent variables deﬁned over high-dimensional parameter spaces such as those of neural network models, using a sampling algorithm such as the Gibbs sampler is prohibitively expensive [36, 34].”
Online gradient-based mixtures for transfer modulation in meta-learning (2018, background): “However, in the setting of latent variables defined over highdimensional parameter spaces such as those of neural network models, a sampling approach such as Gibbs sampling is prohibitively expensive (Neal, 2012; Müller and Insua, 1998).”