Bayesian networks in neuroscience: a survey

Abstract

Bayesian networks are a type of probabilistic graphical models lie at the intersection between statistics and machine learning. They have been shown to be powerful tools to encode dependence relationships among the variables of a domain under uncertainty. Thanks to their generality, Bayesian networks can accommodate continuous and discrete variables, as well as temporal processes. In this paper we review Bayesian networks and how they can be learned automatically from data by means of structure learning algorithms. Also, we examine how a user can take advantage of these networks for reasoning by exact or approximate inference algorithms that propagate the given evidence through the graphical structure. Despite their applicability in many fields, they have been little used in neuroscience, where they have focused on specific problems, like functional connectivity analysis from neuroimaging data. Here we survey key research in neuroscience where Bayesian networks have been used with different aims: discover associations between variables, perform probabilistic reasoning over the model, and classify new observations with and without supervision. The networks are learned from data of any kind–morphological, electrophysiological, -omics and neuroimaging–, thereby broadening the scope–molecular, cellular, structural, functional, cognitive and medical– of the brain aspects to be studied.

Comparison of the EEG Signal Classifiers LDA, NBC and GNBC Based on Time-Frequency Features

“…It is possible to obtain a good classification performance event if attributes are not totally independent. (15) and the classifier output is given by: (16) where: MAP -the maximum a posteriori probability calculated within the space of hypotheses V [28,29]. …”

Inferring functional connectivity in fMRI using minimum partial correlation

“…For references to applications of Bayesian networks in neuroscience, refer to the two recent reviews [27,28] .…”

The Character of Consciousness

“…From the thermodynamic perspective probabilistic inference models, most notably Bayesian models (Knill and Pouget, 2004;Bielza and Larrañaga, 2014) including prior knowledge, mimic natural processes, but the modeled probabilities are not faithful representations of energetics (Equation 3), only parameters. Moreover, the original Markov chain does not carry memory of past events, but only the current state determines the probability distribution of the next state.…”