Zobrazeno 1 - 10
of 102
pro vyhledávání: '"Todor Stefanov"'
Publikováno v:
IEEE Access, Vol 9, Pp 133289-133308 (2021)
CNN design and deployment on embedded edge-processing systems is an error-prone and effort-hungry process, that poses the need for accurate and effective automated assisting tools. In such tools, pre-evaluating the platform-aware CNN metrics such as
Externí odkaz:
https://doaj.org/article/2d3d2edd6f8846438e18a4532d592528
Publikováno v:
IEEE Internet of Things Journal. 10:5843-5858
Autor:
Svetlana Minakova, Todor Stefanov
Publikováno v:
ACM Transactions on Design Automation of Electronic Systems. 28:1-26
Many modern applications require execution of Convolutional Neural Networks (CNNs) on edge devices, such as mobile phones or embedded platforms. This can be challenging, as the state-of-the art CNNs are memory costly, whereas the memory budget of edg
Publikováno v:
ACM Transactions on Embedded Computing Systems. 21:1-33
Convolutional Neural Networks (CNNs) are biologically inspired computational models that are at the heart of many modern computer vision and natural language processing applications. Some of the CNN-based applications are executed on mobile and embed
Publikováno v:
Communications in Computer and Information Science ISBN: 9783031236174
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a4708ab6502c2bbf7aa030986005b80
https://doi.org/10.1007/978-3-031-23618-1_36
https://doi.org/10.1007/978-3-031-23618-1_36
Autor:
Marius Herget, Faezeh Sadat Saadatmand, Martin Bor, Ignacio Gonzalez Alonso, Todor Stefanov, Benny Akesson, Andy D. Pimentel
Publikováno v:
2022 25th Euromicro Conference on Digital System Design (DSD).
Publikováno v:
IEEE Access, Vol 9, Pp 133289-133308 (2021)
IEEE Access, 9, 133289-133308. IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
IEEE Access, 9, 133289-133308. IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
CNN design and deployment on embedded edge-processing systems is an error-prone and effort-hungry process, that poses the need for accurate and effective automated assisting tools. In such tools, pre-evaluating the platform-aware CNN metrics such as
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031045790
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::52eb3db92b5a5017f87971622fe08306
https://doi.org/10.1007/978-3-031-04580-6_9
https://doi.org/10.1007/978-3-031-04580-6_9
Autor:
Erqian Tang, Todor Stefanov
Publikováno v:
Proceedings of the 14th IEEE/ACM International Conference on Utility and Cloud Computing Companion.
Autor:
Todor Stefanov, Svetlana Minakova
Publikováno v:
DSD
2020 23rd Euromicro Conference on Digital System Design (DSD), 133-140. IEEE
STARTPAGE=133;ENDPAGE=140;TITLE=2020 23rd Euromicro Conference on Digital System Design (DSD)
2020 23rd Euromicro Conference on Digital System Design (DSD), 133-140. IEEE
STARTPAGE=133;ENDPAGE=140;TITLE=2020 23rd Euromicro Conference on Digital System Design (DSD)
Nowadays, convolutional neural networks (CNNs) are the core of many intelligent systems, including those that run on mobile and embedded devices. However, the execution of computationally demanding and memory-hungry CNNs on resource-limited mobile an