A New Stochastic Computing Methodology for Efficient Neural Network Implementation

Show simple item record

dc.contributor.author Canals, V.
dc.contributor.author Morro, A.
dc.contributor.author Oliver, A.
dc.contributor.author Alomar, M.L.
dc.contributor.author Rossello, J.L.
dc.date.accessioned 2020-04-28T06:30:22Z
dc.identifier.uri http://hdl.handle.net/11201/152156
dc.description.abstract [eng] This paper presents a new methodology for the hardware implementation of neural networks (NNs) based on probabilistic laws. The proposed encoding scheme circumvents the limitations of classical stochastic computing (based on unipolar or bipolar encoding) extending the representation range to any real number using the ratio of two bipolar-encoded pulsed signals. Furthermore, the novel approach presents practically a total noise-immunity capability due to its specific codification. We introduce different designs for building the fundamental blocks needed to implement NNs. The validity of the present approach is demonstrated through a regression and a pattern recognition task. The low cost of the methodology in terms of hardware, along with its capacity to implement complex mathematical functions (such as the hyperbolic tangent), allows its use for building highly reliable systems and parallel computing.
dc.format application/pdf
dc.relation.isformatof Versió postprint del document publicat a: https://doi.org/10.1109/TNNLS.2015.2413754
dc.relation.ispartof Ieee Transactions On Neural Networks And Learning Systems, 2016, vol. 27, num. 3, p. 551-564
dc.rights (c) IEEE, 2016
dc.subject.classification 53 - Física
dc.subject.other 53 - Physics
dc.title A New Stochastic Computing Methodology for Efficient Neural Network Implementation
dc.type info:eu-repo/semantics/article
dc.type info:eu-repo/semantics/acceptedVersion
dc.date.updated 2020-04-28T06:30:23Z
dc.date.embargoEndDate info:eu-repo/date/embargoEnd/2026-12-31
dc.embargo 2026-12-31
dc.subject.keywords Neural Networks
dc.subject.keywords pattern recognition
dc.subject.keywords probabilistic logic
dc.rights.accessRights info:eu-repo/semantics/embargoedAccess
dc.identifier.doi https://doi.org/10.1109/TNNLS.2015.2413754


Files in this item

This item appears in the following Collection(s)

Show simple item record