Stochastic Pooling Networks

dc.creatorMcDonnell, Mark D.
dc.creatorAmblard, Pierre-Olivier
dc.creatorStocks, Nigel G.
dc.date2009-01-23
dc.date.accessioned2026-07-07T12:33:43Z
dc.date.available2026-07-07T12:33:43Z
dc.descriptionWe introduce and define the concept of a stochastic pooling network (SPN), as a model for sensor systems where redundancy and two forms of 'noise' -- lossy compression and randomness -- interact in surprising ways. Our approach to analyzing SPNs is information theoretic. We define an SPN as a network with multiple nodes that each produce noisy and compressed measurements of the same information. An SPN must combine all these measurements into a single further compressed network output, in a way dictated solely by naturally occurring physical properties -- i.e. pooling -- and yet causes no (or negligible) reduction in mutual information. This means SPNs exhibit redundancy reduction as an emergent property of pooling. The SPN concept is applicable to examples in biological neural coding, nano-electronics, distributed sensor networks, digital beamforming arrays, image processing, multiaccess communication networks and social networks. In most cases the randomness is assumed to be unavoidably present rather than deliberately introduced. We illustrate the central properties of SPNs for several case studies, where pooling occurs by summation, including nodes that are noisy scalar quantizers, and nodes with conditionally Poisson statistics. Other emergent properties of SPNs and some unsolved problems are also briefly discussed.
dc.descriptionPublished, 14 pages of text, 42 references, 4 figures
dc.identifierhttps://arxiv.org/abs/0901.3644
dc.identifierhttp://arxiv.org/abs/0901.3644
dc.identifierJournal of Statistical Mechanics: Theory and Experiment, Art. No. P01012 (2009)
dc.identifierdoi:10.1088/1742-5468/2009/01/P01012
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/217224
dc.subjectStatistical Mechanics
dc.subjectDisordered Systems and Neural Networks
dc.titleStochastic Pooling Networks
dc.typetext

Files

Collections