Publication detail

On Evolutionary Approximation of Sigmoid Function for HW/SW Embedded Systems

MINAŘÍK, M. SEKANINA, L.

Original Title

On Evolutionary Approximation of Sigmoid Function for HW/SW Embedded Systems

Type

conference paper

Language

English

Original Abstract

Providing machine learning capabilities on low cost electronic devices is a challenging goal especially in the context of the Internet of Things paradigm. In order to deliver high performance machine intelligence on low power devices, suitable hardware accelerators have to be introduced. In this paper, we developed a method enabling to evolve a hardware implementation together with a corresponding software controller for key components of smart embedded systems. The proposed approach is based on a multi-objective design space exploration conducted by means of extended linear genetic programming. The approach was evaluated in the task of approximate sigmoid function design which is an important component of hardware implementations of neural networks. During these experiments, we automatically re-discovered some approximate sigmoid functions known from the literature. The method was implemented as an extension of an existing platform supporting concurrent evolution of hardware and software of embedded systems.

Keywords

Sigmoid, Linear genetic programming, HW/SW co-design

Authors

MINAŘÍK, M.; SEKANINA, L.

Released

19. 4. 2017

Publisher

Springer International Publishing

Location

Berlin

ISBN

978-3-319-55696-3

Book

20th European Conference on Genetic Programming, EuroGP 2017

Edition

Lecture Notes in Computer Science

Pages from

343

Pages to

358

Pages count

16

URL

BibTex

@inproceedings{BUT135902,
  author="Miloš {Minařík} and Lukáš {Sekanina}",
  title="On Evolutionary Approximation of Sigmoid Function for HW/SW Embedded Systems",
  booktitle="20th European Conference on Genetic Programming, EuroGP 2017",
  year="2017",
  series="Lecture Notes in Computer Science",
  volume="10196",
  pages="343--358",
  publisher="Springer International Publishing",
  address="Berlin",
  doi="10.1007/978-3-319-55696-3\{_}22",
  isbn="978-3-319-55696-3",
  url="https://www.fit.vut.cz/research/publication/11298/"
}