Detail výsledku

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.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Badáň Filip, Ing.
Sekanina Lukáš, prof. Ing., Ph.D., UPSY (FIT)
Abstrakt

Automateddesign methods for convolutional neural networks (CNNs) have recently beendeveloped in order to increase the design productivity. We propose aneuroevolution method capable of evolving and optimizing CNNs with respect tothe classification error and CNN complexity (expressed as the number of tunableCNN parameters), in which the inference phase can partly be executed usingfixed point operations to further reduce power consumption. Experimentalresults are obtained with TinyDNN framework and presented using two common imageclassification benchmark problems - MNIST and CIFAR-10.

Klíčová slova

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

Rok
2019
Strany
109–121
Sborník
Theory and Practice of Natural Computing
Řada
LNCS 11934
Konference
8th International Conference on the Theory and Practice of Natural Computing 2019
ISBN
978-3-030-34499-3
Vydavatel
Springer International Publishing
Místo
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/"
}
Soubory
Projekty
IT4Innovations excellence in science, MŠMT, Národní program udržitelnosti II, LQ1602, zahájení: 2016-01-01, ukončení: 2020-12-31, ukončen
Pokročilé metody nature-inspired optimalizačních algoritmů a HPC implementace pro řešení reálných aplikací, MŠMT, INTER-EXCELLENCE - Podprogram INTER-COST, LTC18053, zahájení: 2018-06-01, ukončení: 2020-02-29, ukončen
Výzkumné skupiny
Výzkumná skupina Evolvable Hardware (VZ EHW)
Pracoviště
Ústav počítačových systémů (UPSY)
Nahoru