prikaz prve stranice dokumenta Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython
  Download
PDF 1.58 MB
Scientific paper - Original scientific paper
Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython
In: Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology. Tirana: University of Tirana, 2021. pp. 67-73. urn:nbn:hr:112:223963
Đokić, Kristian; Mikolčević, Hrvoje; Radišić, Bojan

Cite this document

Đokić, K., Mikolčević, H. & Radišić, B. (2021). Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython. Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology (pp. 67-73). Tirana: University of Tirana. Retrieved from https://urn.nsk.hr/urn:nbn:hr:112:223963

Đokić, Kristian, et al. "Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython." Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology, University of Tirana, 2021, pp. 67-73. https://urn.nsk.hr/urn:nbn:hr:112:223963

Đokić, Kristian, Hrvoje Mikolčević and Bojan Radišić. "Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython." In Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology, 67-73. Tirana: University of Tirana, 2021. Accessed 2025 January 25. https://urn.nsk.hr/urn:nbn:hr:112:223963

Đokić, K., Mikolčević, H. and Radišić, B. (2021) 'Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython', Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology, University of Tirana, Tirana, pp. 67-73. Available at: https://urn.nsk.hr/urn:nbn:hr:112:223963 (Accessed 25 January 2025)

Đokić K, Mikolčević H, Radišić B. Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython. Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology. Tirana: University of Tirana; 2021. Pp. 67-73. [cited 2025 January 25] Available at: https://urn.nsk.hr/urn:nbn:hr:112:223963

K. Đokić, H. Mikolčević and B. Radišić, "Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython", Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology Tirana: University of Tirana, 2021. [Online] Available at: https://urn.nsk.hr/urn:nbn:hr:112:223963 [Accessed: 25 January 2025]

Please login to the repository to save this object to your list.
Metadata
Title (english)Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython
AuthorKristian Đokić
AuthorHrvoje Mikolčević
AuthorBojan Radišić
Author's institutionPolytehnic in Pozega
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract (english)
In recent years we have witnessed the rapid development of machine learning algorithms, and the same can be said for IoT. Developments in both fields have also influenced the growth of machine learning algorithms in IoT devices. The authors of a series of papers cite several reasons to argue this trend. This paper explores the possibility of using the Python programming language in different versions to create, train, and implement convolutional neural networks on two SoCs based on different architectures (ARM and RISC-V). The influence of the number of filters in the convolutional layer on the inference speed is also investigated. The number of filters has a different effect on inference speed depending on the existence of additional components that accelerate individual operations of convolutional neural networks (convolution, batch normalization, activation, and pooling operations).
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review - international
Publication versionPublished version
Publication titleProceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology
Numberingpp. 67-73
e-ISSN1613-0073
URN:NBNurn:nbn:hr:112:223963
Publication2021
ConferenceTitle: 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology (CSIT 2021)
Location: Tirana, Albania
Start date: 2021-05-21
End date: 2021-05-22
Assembly type: Lecture
Document URLhttps://ceur-ws.org/Vol-2872/paper10.pdf
Type of resourceText
PublisherUniversity of Tirana
Publishing placeTirana
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2024-05-03 10:49:41