Neuro inspired reconfigurable architecture for hardware/software co-design

Arfan Ghani; Liam McDaid; Ammar Belatreche; Waqar Ahmed

doi:10.1109/SOCCON.2009.5398039

Neuro inspired reconfigurable architecture for hardware/software co-design

Arfan Ghani
, Liam McDaid
, Ammar Belatreche
, Waqar Ahmed

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

2 Citations (Scopus)

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.

Original language	English
Title of host publication	Proceedings: IEEE International SOC Conference
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	287-290
Number of pages	4
ISBN (Print)	978-1-4244-5220-0
DOIs	https://doi.org/10.1109/SOCCON.2009.5398039
Publication status	Published - 2009
Event	2009 IEEE International SOC Conference (SOCC) - Belfast, United Kingdom Duration: 9 Sept 2009 → 11 Sept 2009

Conference

Conference	2009 IEEE International SOC Conference (SOCC)
Country/Territory	United Kingdom
City	Belfast
Period	9/09/09 → 11/09/09

Keywords

cortical column
neuro inspired reconfigurable architecture
neuro-inspired computing
microcircuits
FPGA
speech recognition
floating-point software
fixed-point hardware-software co-design technique

Access to Document

10.1109/SOCCON.2009.5398039

Cite this

Ghani, A, McDaid, L, Belatreche, A & Ahmed, W 2009, Neuro inspired reconfigurable architecture for hardware/software co-design. in Proceedings: IEEE International SOC Conference. Institute of Electrical and Electronics Engineers Inc., pp. 287-290, 2009 IEEE International SOC Conference (SOCC), Belfast, United Kingdom, 9/09/09. https://doi.org/10.1109/SOCCON.2009.5398039

@inproceedings{b3c575836f1f40d297bb39a309e0fe00,

title = "Neuro inspired reconfigurable architecture for hardware/software co-design",

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 = "cortical column, neuro inspired reconfigurable architecture, neuro-inspired computing, microcircuits, FPGA, speech recognition, floating-point software, fixed-point hardware-software co-design technique",

author = "Arfan Ghani and Liam McDaid and Ammar Belatreche and Waqar Ahmed",

year = "2009",

doi = "10.1109/SOCCON.2009.5398039",

language = "English",

isbn = "978-1-4244-5220-0",

pages = "287--290",

booktitle = "Proceedings: IEEE International SOC Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2009 IEEE International SOC Conference (SOCC) ; Conference date: 09-09-2009 Through 11-09-2009",

}

TY - GEN

T1 - Neuro inspired reconfigurable architecture for hardware/software co-design

AU - Ghani, Arfan

AU - McDaid, Liam

AU - Belatreche, Ammar

AU - Ahmed, Waqar

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

KW - cortical column

KW - neuro inspired reconfigurable architecture

KW - neuro-inspired computing

KW - microcircuits

KW - FPGA

KW - speech recognition

KW - floating-point software

KW - fixed-point hardware-software co-design technique

U2 - 10.1109/SOCCON.2009.5398039

DO - 10.1109/SOCCON.2009.5398039

M3 - Conference proceeding

SN - 978-1-4244-5220-0

SP - 287

EP - 290

BT - Proceedings: IEEE International SOC Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2009 IEEE International SOC Conference (SOCC)

Y2 - 9 September 2009 through 11 September 2009

ER -

Neuro inspired reconfigurable architecture for hardware/software co-design

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this