Naslov
Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython
(Inference speed comparison using convolutions in neural networks on various SoC hardware platforms using MicroPython)

Autori
Đokić, Kristian ; Mikolčević, Hrvoje ; Radišić, Bojan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 4th International Conference on Recent Trends and Applications in Computer Science and Information Technology / Xhina, Endrit ; Hoxha, Klesti - Tirana : University of Tirana, 2021, 67-73

Skup
4th International Conference on Recent Trends and Applications in Computer Science and Information Technology (CSIT 2021)

Mjesto i datum
Tirana, Albanija, 21.05.2021. - 22.05.2021

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
CNN ; Convolution Neural Network ; MicroPython ; RISC-V ; SoC

Sažetak
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).

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti

POVEZANOST RADA