Detail publikace

Hardware-Aware Evolutionary Approaches to Deep Neural Networks

SEKANINA, L. MRÁZEK, V. PIŇOS, M.

Originální název

Hardware-Aware Evolutionary Approaches to Deep Neural Networks

Typ

kapitola v knize

Jazyk

angličtina

Originální abstrakt

This chapter gives an overview of evolutionary algorithm (EA) based methods applied to the design of efficient implementations of deep neural networks (DNN). We introduce various acceleration hardware platforms for DNNs developed especially for energy-efficient computing in edge devices. In addition to evolutionary optimization of their particular components or settings, we will describe neural architecture search (NAS) methods adopted to directly design highly optimized DNN architectures for a given hardware platform. Techniques that co-optimize hardware platforms and neural network architecture to maximize the accuracy-energy trade-offs will be emphasized. Case studies will primarily be devoted to NAS for image classification. Finally, the open challenges of this popular research area will be discussed.

Klíčová slova

deep neural network, evolutionary algorithm, hardware accelerator, inference, image classification

Autoři

SEKANINA, L.; MRÁZEK, V.; PIŇOS, M.

Vydáno

1. 11. 2023

Nakladatel

Springer Nature Singapore

Místo

Singapore

ISBN

978-981-9938-13-1

Kniha

Handbook of Evolutionary Machine Learning

Edice

Genetic and Evolutionary Computation

Strany od

367

Strany do

396

Strany počet

30

URL

https://link.springer.com/chapter/10.1007/978-981-99-3814-8_12

BibTex

@inbook{BUT185298,
  author="Lukáš {Sekanina} and Vojtěch {Mrázek} and Michal {Piňos}",
  title="Hardware-Aware Evolutionary Approaches to Deep Neural Networks",
  booktitle="Handbook of Evolutionary Machine Learning",
  year="2023",
  publisher="Springer Nature Singapore",
  address="Singapore",
  series="Genetic and Evolutionary Computation",
  pages="367--396",
  doi="10.1007/978-981-99-3814-8\{_}12",
  isbn="978-981-9938-13-1",
  url="https://link.springer.com/chapter/10.1007/978-981-99-3814-8_12"
}

Dokumenty

sekanina_bch2024web.pdf