Publication:
LSTM-type Neural Network Implementation on a Processor Based on Neuromatrix and RISC Cores for Resource-Limited Applications

Простая страница элемента
dc.contributor.authorLandyshev, S.
dc.contributor.authorZholondkovskiy, V.
dc.contributor.authorBocharov, Y.
dc.contributor.authorButuzov, V.
dc.contributor.authorБочаров, Юрий Иванович
dc.contributor.authorБутузов, Владимир Алексеевич
dc.date.accessioned2024-11-27T09:22:01Z
dc.date.available2024-11-27T09:22:01Z
dc.date.issued2020
dc.description.abstract© 2020 IEEE.In this paper, we consider the implementation of a recurrent artificial neural network LSTM on the NM6407 digital signal processor (DSP) that is optimized for performing vector and matrix calculations. It contains two NeuroMatrix NMC4 cores, each of which includes RISC processor and vector coprocessor. The architectural features and processor resources are considered, as well as an assessment of its performance in the implementation of the LSTM network to solve a typical classification problem. The implementation of this type of network on the NM6407 tensor core accelerated computations by a factor of 15-350 compared to a scalar processor.
dc.identifier.citationLSTM-type Neural Network Implementation on a Processor Based on Neuromatrix and RISC Cores for Resource-Limited Applications / Landyshev, S. [et al.] // 2020 22th International Conference on Digital Signal Processing and its Applications, DSPA 2020. - 2020. - 10.1109/DSPA48919.2020.9213291
dc.identifier.doi10.1109/DSPA48919.2020.9213291
dc.identifier.urihttps://www.doi.org/10.1109/DSPA48919.2020.9213291
dc.identifier.urihttps://www.scopus.com/record/display.uri?eid=2-s2.0-85094559366&origin=resultslist
dc.identifier.urihttps://openrepository.mephi.ru/handle/123456789/22538
dc.relation.ispartof2020 22th International Conference on Digital Signal Processing and its Applications, DSPA 2020
dc.titleLSTM-type Neural Network Implementation on a Processor Based on Neuromatrix and RISC Cores for Resource-Limited Applications
dc.typeConference Paper
dspace.entity.typePublication
relation.isAuthorOfPublication3be06e9c-ebcc-44af-90c4-6dda6baf328f
relation.isAuthorOfPublicationfc14ee49-3c57-4f20-a95c-664996007e8f
relation.isAuthorOfPublication.latestForDiscovery3be06e9c-ebcc-44af-90c4-6dda6baf328f
relation.isOrgUnitOfPublication06e1796d-4f55-4057-8d7e-bb2f3b5676f5
relation.isOrgUnitOfPublication.latestForDiscovery06e1796d-4f55-4057-8d7e-bb2f3b5676f5
Файлы
Коллекции
Публикации