Publication:
Extraction of Significant Features by Fixed-Weight Layer of Processing Elements for the Development of an Efficient Spiking Neural Network Classifier

Простая страница элемента
dc.contributor.authorSboev, A.
dc.contributor.authorRybka, R.
dc.contributor.authorKunitsyn, D.
dc.contributor.authorSerenko, A.
dc.contributor.authorСбоев, Александр Георгиевич
dc.date.accessioned2024-12-27T12:40:38Z
dc.date.available2024-12-27T12:40:38Z
dc.date.issued2023
dc.description.abstractIn this paper, we demonstrate that fixed-weight layers generated from random distribution or logistic functions can effectively extract significant features from input data, resulting in high accuracy on a variety of tasks, including Fisher’s Iris, Wisconsin Breast Cancer, and MNIST datasets. We have observed that logistic functions yield high accuracy with less dispersion in results. We have also assessed the precision of our approach under conditions of minimizing the number of spikes generated in the network. It is practically useful for reducing energy consumption in spiking neural networks. Our findings reveal that the proposed method demonstrates the highest accuracy on Fisher’s iris and MNIST datasets with decoding using logistic regression. Furthermore, they surpass the accuracy of the conventional (non-spiking) approach using only logistic regression in the case of Wisconsin Breast Cancer. We have also investigated the impact of non-stochastic spike generation on accuracy.
dc.identifier.citationExtraction of Significant Features by Fixed-Weight Layer of Processing Elements for the Development of an Efficient Spiking Neural Network Classifier / Sboev, A. [et al.] // Big Data and Cognitive Computing. - 2023. - 7. - № 4. - 10.3390/bdcc7040184
dc.identifier.doi10.3390/bdcc7040184
dc.identifier.urihttps://www.doi.org/10.3390/bdcc7040184
dc.identifier.urihttps://www.scopus.com/record/display.uri?eid=2-s2.0-85180465931&origin=resultslist
dc.identifier.urihttps://openrepository.mephi.ru/handle/123456789/29552
dc.relation.ispartofBig Data and Cognitive Computing
dc.subjectMNIST database
dc.subjectSpiking Neurons
dc.subjectBrain-inspired Computing
dc.subjectWorking Memory
dc.subjectKurtosis
dc.titleExtraction of Significant Features by Fixed-Weight Layer of Processing Elements for the Development of an Efficient Spiking Neural Network Classifier
dc.typeArticle
dspace.entity.typePublication
oaire.citation.issue4
oaire.citation.volume7
relation.isAuthorOfPublicationfc2d63d7-5260-41ba-a952-0420c8848b13
relation.isAuthorOfPublication.latestForDiscoveryfc2d63d7-5260-41ba-a952-0420c8848b13
relation.isOrgUnitOfPublicationba0b4738-e6bd-4285-bda5-16ab2240dbd1
relation.isOrgUnitOfPublication010157d0-1f75-46b2-ab5b-712e3424b4f5
relation.isOrgUnitOfPublication.latestForDiscoveryba0b4738-e6bd-4285-bda5-16ab2240dbd1
Файлы
Original bundle
Теперь показываю 1 - 1 из 1
Уменьшенное изображение
Name:
W4389893358.pdf
Size:
919.34 KB
Format:
Adobe Portable Document Format
Description:
Download
Коллекции
Публикации