Neuro inspired reconfigurable architecture for hardware/software co-design

Author

Ghani, Arfan ; McDaid, Liam J. ; Belatreche, Ammar ; Ahmed, Waqar

Author_Institution

Intell. Syst. Res. Centre, Univ. of Ulster, Derry, UK

fYear

2009

fDate

9-11 Sept. 2009

Firstpage

287

Lastpage

290

Abstract

In neuro-inspired computing, cortical columns or microcircuits appear to be the basic unit of computation for recognition related tasks. This paper proposes an integrated framework for an efficient implementation of a cortical column on reconfigurable platform (FPGAs). A novel hardware/software co-design implementation strategy is devised and the functionality is tested in the context of speech recognition application. An overall accuracy of 98% was achieved with the fixed-point hardware/software co-design technique in comparison to the 100% with the floating-point software implementation.

Keywords

field programmable gate arrays; hardware-software codesign; neural chips; neural net architecture; reconfigurable architectures; FPGA; cortical column; fixed-point hardware-software co-design technique; floating-point software; microcircuits; neuro inspired reconfigurable architecture; neuro-inspired computing; speech recognition; Application software; Computer architecture; Computer networks; Field programmable gate arrays; Hardware; Neurons; Reconfigurable architectures; Recurrent neural networks; Software testing; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

SOC Conference, 2009. SOCC 2009. IEEE International

Conference_Location

Belfast

Print_ISBN

978-1-4244-4940-8

Electronic_ISBN

978-1-4244-4941-5

Type

conf

DOI

10.1109/SOCCON.2009.5398039

Filename

5398039