Spiking Neuron Network Helmhotz Machine

DSpace Repository

Show simple item record

dc.contributor.author Sountsov, Pavel
dc.contributor.author Miller, Paul
dc.date.accessioned 2016-02-11T23:45:26Z
dc.date.available 2016-02-11T23:45:26Z
dc.date.issued 2015-04-21
dc.identifier.citation Sountsov P and MillerP (2015) Spiking neuron network Helmholtz machine. Front. Comput. Neurosci. 9:46. doi: 10.3389/fncom.2015.00046
dc.identifier.issn 1662-5188
dc.identifier.uri http://hdl.handle.net/10192/31592
dc.description.abstract An increasing amount of behavioral and neurophysiological data suggests that the brain performs optimal (or near-optimal) probabilistic inference and learning during perception and other tasks. Although many machine learning algorithms exist that perform inference and learning in an optimal way, the complete description of how one of those algorithms (or a novel algorithm) can be implemented in the brain is currently incomplete. There have been many proposed solutions that address how neurons can perform optimal inference but the question of how synaptic plasticity can implement optimal learning is rarely addressed. This paper aims to unify the two fields of probabilistic inference and synaptic plasticity by using a neuronal network of realistic model spiking neurons to implement a well-studied computational model called the Helmholtz Machine. The Helmholtz Machine is amenable to neural implementation as the algorithm it uses to learn its parameters, called the wake-sleep algorithm, uses a local delta learning rule. Our spiking-neuron network implements both the delta rule and a small example of a Helmholtz machine. This neuronal network can learn an internal model of continuous-valued training data sets without supervision. The network can also perform inference on the learned internal models. We show how various biophysical features of the neural implementation constrain the parameters of the wake-sleep algorithm, such as the duration of the wake and sleep phases of learning and the minimal sample duration. We examine the deviations from optimal performance and tie them to the properties of the synaptic plasticity rule.
dc.description.sponsorship Brandeis University Open Access Fund, Computational Neuroscience Training Grant (T90 DA032435) and IGERT Theory grant (DGE106820).
dc.language English
dc.language.iso eng
dc.publisher Frontiers
dc.rights Copyright by the authors 2015
dc.title Spiking Neuron Network Helmhotz Machine
dc.type Article
dc.contributor.department Department of Biology
dc.identifier.doi http://dx.doi.org/10.3389/fncom.2015.00046
dc.description.esploro yes

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search BIR


My Account