An energy efficient additive neural network

Simple item page
buir.contributor.authorÇetin, A. Enis
buir.contributor.orcidÇetin, A. Enis|0000-0002-3449-1958
dc.contributor.authorAfrasiyabi, A.en_US
dc.contributor.authorNasir, B.en_US
dc.contributor.authorYıldız, O.en_US
dc.contributor.authorYarman-Vural, F. T.en_US
dc.contributor.authorÇetin, A. Enisen_US
dc.coverage.spatialAntalya, Turkeyen_US
dc.date.accessioned2018-04-12T11:45:09Z
dc.date.available2018-04-12T11:45:09Z
dc.date.issued2017en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 15-18 May 2017en_US
dc.descriptionConference Name: IEEE 25th Signal Processing and Communications Applications Conference, SIU 2017en_US
dc.description.abstractIn this paper, we propose a new energy efficient neural network with the universal approximation property over space of Lebesgue integrable functions. This network, called additive neural network, is very suitable for mobile computing. The neural structure is based on a novel vector product definition, called ef-operator, that permits a multiplier-free implementation. In ef-operation, the 'product' of two real numbers is defined as the sum of their absolute values, with the sign determined by the sign of the product of the numbers. This 'product' is used to construct a vector product in n-dimensional Euclidean space. The vector product induces the lasso norm. The proposed additive neural network successfully solves the XOR problem. The experiments on MNIST dataset show that the classification performances of the proposed additive neural networks are very similar to the corresponding multi-layer perceptron.en_US
dc.identifier.doi10.1109/SIU.2017.7960263en_US
dc.identifier.urihttp://hdl.handle.net/11693/37598
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/SIU.2017.7960263en_US
dc.source.titleProceedings of the IEEE 25th Signal Processing and Communications Applications Conference, SIU 2017en_US
dc.subjectEfficient ANNen_US
dc.subjectEnergy efficienten_US
dc.subjectMachine learningen_US
dc.subjectMnisten_US
dc.subjectMultiplierless annen_US
dc.subjectXORen_US
dc.subjectArtificial intelligenceen_US
dc.subjectLearning systemsen_US
dc.subjectNeural networksen_US
dc.subjectLebesgue integrable functionsen_US
dc.subjectUniversal approximation propertiesen_US
dc.titleAn energy efficient additive neural networken_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
An energy efficient additive neural network.pdf
Size:
452.48 KB
Format:
Adobe Portable Document Format
Description:
Full Printable Version
Download

Collections

Department of Electrical and Electronics Engineering