Detail publikačního výsledku

Efficient Hardware Accelerator for Symbolic Regression Problems

VAŠÍČEK, Z.; SEKANINA, L.

Original Title

Efficient Hardware Accelerator for Symbolic Regression Problems

English Title

Efficient Hardware Accelerator for Symbolic Regression Problems

Type

Paper in proceedings outside WoS and Scopus

Original Abstract

In this paper, a new hardware architecture for the acceleration of symbolic regression problems using Cartesian Genetic Programming (CGP) is presented.
In order to minimize the number of expensive memory accesses, a new algorithm is proposed.
The search algorithm is implemented using PowerPC processor which is available in Xilinx FPGAs of Virtex family.
A significant speedup of evolution is obtained in comparison with a highly optimized software implementation of CGP.

English abstract

In this paper, a new hardware architecture for the acceleration of symbolic regression problems using Cartesian Genetic Programming (CGP) is presented.
In order to minimize the number of expensive memory accesses, a new algorithm is proposed.
The search algorithm is implemented using PowerPC processor which is available in Xilinx FPGAs of Virtex family.
A significant speedup of evolution is obtained in comparison with a highly optimized software implementation of CGP.

Keywords

hardware acceleration, regression problem, evolutionary design, image filter, fpga, powerpc

Key words in English

hardware acceleration, regression problem, evolutionary design, image filter, fpga, powerpc

Authors

VAŠÍČEK, Z.; SEKANINA, L.

RIV year

2010

Released

13.11.2009

Publisher

Masaryk University

Location

Znojmo

ISBN

978-80-87342-04-6

Book

5th Doctoral Workshop on Mathematical and Engineering Methods in Computer Science

Pages from

192

Pages to

199

Pages count

8

URL

https://www.fit.vut.cz/research/publication/9108/

Full text in the Digital Library

http://hdl.handle.net/

BibTex

@inproceedings{BUT34289,
  author="Zdeněk {Vašíček} and Lukáš {Sekanina}",
  title="Efficient Hardware Accelerator for Symbolic Regression Problems",
  booktitle="5th Doctoral Workshop on Mathematical and Engineering Methods in Computer Science",
  year="2009",
  pages="192--199",
  publisher="Masaryk University",
  address="Znojmo",
  isbn="978-80-87342-04-6",
  url="https://www.fit.vut.cz/research/publication/9108/"
}

Documents

paper