Browse DORAS
Browse Theses
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

Towards hardware acceleration of neuroevolution for multimedia processing applications on mobile devices

Larkin, Daniel and Kinane, Andrew and O'Connor, Noel E. (2006) Towards hardware acceleration of neuroevolution for multimedia processing applications on mobile devices. In: ICONIP 2006 - International Conference on Neural Information Processing, 3-6 October 2006, Hong Kong, China. ISBN 978-3-540-46484-6

Full text available as:

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


This paper addresses the problem of accelerating large artificial neural networks (ANN), whose topology and weights can evolve via the use of a genetic algorithm. The proposed digital hardware architecture is capable of processing any evolved network topology, whilst at the same time providing a good trade off between throughput, area and power consumption. The latter is vital for a longer battery life on mobile devices. The architecture uses multiple parallel arithmetic units in each processing element (PE). Memory partitioning and data caching are used to minimise the effects of PE pipeline stalling. A first order minimax polynomial approximation scheme, tuned via a genetic algorithm, is used for the activation function generator. Efficient arithmetic circuitry, which leverages modified Booth recoding, column compressors and carry save adders, is adopted throughout the design.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Additional Information:The original publication is available at
Subjects:Computer Science > Computer networks
Computer Science > Information technology
DCU Faculties and Centres:Research Initiatives and Centres > Centre for Digital Video Processing (CDVP)
Published in:Neural Information Processing. Lecture Notes in Computer Science 4234. Springer Berlin / Heidelberg. ISBN 978-3-540-46484-6
Publisher:Springer Berlin / Heidelberg
Official URL:
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Enterprise Ireland
ID Code:455
Deposited On:21 May 2008 by DORAS Administrator. Last Modified 05 May 2010 14:36

Download statistics

Archive Staff Only: edit this record