Blind separation of nonlinear mixtures by variational Bayesian learning

Honkela, Antti; Valpola, Harri; Ilin, Alexander; Karhunen, Juha

doi:10.1016/j.dsp.2007.02.009

Cited by 21 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, maximization after marginalizing s out of the posterior is thought to prevent overfitting by avoiding arbitrary peaks of the joint posterior, leading to a better estimate of the posterior mass concentration. Variational Bayes (VB) approaches, such as ensemble learning [53], [54], carry out marginalization while approximating the joint posterior by a product of factors, each corresponding to a subset of the model (and noise) parameters θ . Marginalization can also simplify to the likelihood function when a “constant” prior is used for θ .…”

Section: A Unified Framework For Subspace Modeling and Developmentmentioning

confidence: 99%

Blind Source Separation for Unimodal and Multimodal Brain Networks: A Unifying Framework for Subspace Modeling

Silva

Plis

Sui

et al. 2016

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

In the past decade, numerous advances in the study of the human brain were fostered by successful applications of blind source separation (BSS) methods to a wide range of imaging modalities. The main focus has been on extracting “networks” represented as the underlying latent sources. While the broad success in learning latent representations from multiple datasets has promoted the wide presence of BSS in modern neuroscience, it also introduced a wide variety of objective functions, underlying graphical structures, and parameter constraints for each method. Such diversity, combined with a host of datatype-specific know-how, can cause a sense of disorder and confusion, hampering a practitioner’s judgment and impeding further development. We organize the diverse landscape of BSS models by exposing its key features and combining them to establish a novel unifying view of the area. In the process, we unveil important connections among models according to their properties and subspace structures. Consequently, a high-level descriptive structure is exposed, ultimately helping practitioners select the right model for their applications. Equipped with that knowledge, we review the current state of BSS applications to neuroimaging. The gained insight into model connections elicits a broader sense of generalization, highlighting several directions for model development. In light of that, we discuss emerging multi-dataset multidimensional (MDM) models and summarize their benefits for the study of the healthy brain and disease-related changes.

show abstract

Section: A Unified Framework For Subspace Modeling and Developmentmentioning

confidence: 99%

Blind Source Separation for Unimodal and Multimodal Brain Networks: A Unifying Framework for Subspace Modeling

Silva

Plis

Sui

et al. 2016

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Several extensions of the basic ICA model have been proposed to improve its performance; they are commonly referred to as semi-blind independent component analysis (see [5] for a review). The main approaches exploit nonlinear mixtures [20], temporal correlation [4], positivity [9], or sparsity [19,23,34]. An approach to modelling class-conditional densities based on an IFA model was also recently introduced in [25].…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of a railway device using semi-supervised independent factor analysis with mixing constraints

Côme

Oukhellou

Denœux

et al. 2011

Pattern Anal Applic

View full text Add to dashboard Cite

Independent factor analysis (IFA) defines a generative model for observed data that are assumed to be linear mixtures of some unknown non-Gaussian, mutually independent latent variables (also called sources or independent components). The probability density function of each individual latent variable is modelled by a mixture of Gaussians. Learning in the context of this model is usually performed within an unsupervised framework in which only unlabelled samples are used. Both the mixing matrix and the parameters of latent variable densities are learned from the observed data. This paper investigates the possibility of estimating an IFA model in a noiseless setting when two kinds of prior information are incorporated, namely constraints on the mixing process and partial knowledge on the cluster membership of some training samples. Semi-supervised or partially supervised learning frameworks can thus be handled. The investigation of these two kinds of prior information was motivated by a realworld application concerning the fault diagnosis of railway track circuits. Simulated data, resulting from both these applications, are provided to demonstrate the capacity of our approach to enhance estimation accuracy and remove the indeterminacy commonly encountered in unsupervised IFA, such as source permutations.

show abstract

“…Bayesian NLICA methods were proposed in [62] and [63]. Some tests were conduced in [64] to compare the experimental recovery performance of both Bayesian and structural constrained algorithms (PNL model) for nonlinear mixed signals.…”

Section: As Described In Equation 26mentioning

confidence: 99%

Nonlinear Independent Component Analysis: Theoretical Review And Applications

Filho¹,

Seixas²

2007

L&NLM

View full text Add to dashboard Cite

-This paper reviews the Nonlinear Independent Components Analysis and its applications to blind source separation. An overview of the main statistical principles that guide the search for the independent components is formulated. The uniqueness of solution and some algorithms for estimating the nonlinear independent components are discussed. Experimental results using a synthetic database are used for performance comparison. A practical application in experimental high-energy physics is also presented.

show abstract

Blind separation of nonlinear mixtures by variational Bayesian learning

Cited by 21 publications

References 24 publications

Blind Source Separation for Unimodal and Multimodal Brain Networks: A Unifying Framework for Subspace Modeling

Blind Source Separation for Unimodal and Multimodal Brain Networks: A Unifying Framework for Subspace Modeling

Fault diagnosis of a railway device using semi-supervised independent factor analysis with mixing constraints

Nonlinear Independent Component Analysis: Theoretical Review And Applications

Contact Info

Product

Resources

About