Publication detail

Hardware-Aware Evolutionary Approaches to Deep Neural Networks

SEKANINA, L. MRÁZEK, V. PIŇOS, M.

Original Title

Hardware-Aware Evolutionary Approaches to Deep Neural Networks

Type

book chapter

Language

English

Original Abstract

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.

Keywords

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

Authors

SEKANINA, L.; MRÁZEK, V.; PIŇOS, M.

Released

1. 11. 2023

Publisher

Springer Nature Singapore

Location

Singapore

ISBN

978-981-9938-13-1

Book

Handbook of Evolutionary Machine Learning

Edition

Genetic and Evolutionary Computation

Pages from

367

Pages to

396

Pages count

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"
}

Documents

sekanina_bch2024web.pdf