Publication Details

Optimizing Convolutional Neural Networks for Embedded Systems By Means of Neuroevolution

BADÁŇ, F.; SEKANINA, L. Optimizing Convolutional Neural Networks for Embedded Systems By Means of Neuroevolution. In Theory and Practice of Natural Computing. LNCS 11934. Cham: Springer International Publishing, 2019. p. 109-121. ISBN: 978-3-030-34499-3.

Czech title

Optimalizace konvolučních neuronových sítí pro vestavěné systémy s využitím neuroevoluce

Type

conference paper

Language

English

Authors

Badáň Filip, Ing.
Sekanina Lukáš, prof. Ing., Ph.D. (DCSY)

Keywords

Evolutionary Algorithm, Convolutional neural network, Neuroevolution, Embedded Systems, Energy Efficiency

Abstract

Automated design methods for convolutional neural networks (CNNs) have recently been developed in order to increase the design productivity. We propose a neuroevolution method capable of evolving and optimizing CNNs with respect to the classification error and CNN complexity (expressed as the number of tunable CNN parameters), in which the inference phase can partly be executed using fixed point operations to further reduce power consumption. Experimental results are obtained with TinyDNN framework and presented using two common image classification benchmark problems - MNIST and CIFAR-10.

Published

2019

Pages

109–121

Proceedings

Theory and Practice of Natural Computing

Series

LNCS 11934

ISBN

978-3-030-34499-3

Publisher

Springer International Publishing

Place

Cham

DOI

10.1007/978-3-030-34500-6_7

UT WoS

000611522600007

EID Scopus

2-s2.0-85077000581

BibTeX

@inproceedings{BUT161459,
  author="Filip {Badáň} and Lukáš {Sekanina}",
  title="Optimizing Convolutional Neural Networks for Embedded Systems By Means of Neuroevolution",
  booktitle="Theory and Practice of Natural Computing",
  year="2019",
  series="LNCS 11934",
  pages="109--121",
  publisher="Springer International Publishing",
  address="Cham",
  doi="10.1007/978-3-030-34500-6\{_}7",
  isbn="978-3-030-34499-3",
  url="https://www.fit.vut.cz/research/publication/12045/"
}