Faculty of Information Technology, BUT

Publication Details

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

MINAŘÍK Miloš and SEKANINA Lukáš. On Evolutionary Approximation of Sigmoid Function for HW/SW Embedded Systems. In: 20th European Conference on Genetic Programming, EuroGP 2017. Lecture Notes in Computer Science, vol. 10196. Berlin: Springer International Publishing, 2017, pp. 343-358. ISBN 978-3-319-55696-3.
Czech title
O evoluční aproximaci sigmoidy for HW/SW vestavěné systémy
Type
conference paper
Language
english
Authors
Keywords
Sigmoid, Linear genetic programming, HW/SW co-design
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.
Published
2017
Pages
343-358
Proceedings
20th European Conference on Genetic Programming, EuroGP 2017
Series
Lecture Notes in Computer Science
Volume
10196
Conference
20th European Conference on Genetic Programming, Amsterdam, NL
ISBN
978-3-319-55696-3
Publisher
Springer International Publishing
Place
Berlin, DE
DOI
BibTeX
@INPROCEEDINGS{FITPUB11298,
   author = "Milo\v{s} Mina\v{r}\'{i}k and Luk\'{a}\v{s} Sekanina",
   title = "On Evolutionary Approximation of Sigmoid Function for HW/SW Embedded Systems",
   pages = "343--358",
   booktitle = "20th European Conference on Genetic Programming, EuroGP 2017",
   series = "Lecture Notes in Computer Science",
   volume = 10196,
   year = 2017,
   location = "Berlin, DE",
   publisher = "Springer International Publishing",
   ISBN = "978-3-319-55696-3",
   doi = "10.1007/978-3-319-55696-3\_22",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11298"
}
Files
Back to top