Neuro inspired reconfigurable architecture for hardware/software co-design
作者： Arfan Ghani , Liam J McDaid , Ammar Belatreche , Waqar Ahmed
DOI: 10.1109/SOCCON.2009.5398039
关键词:
摘要: 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 efficient implementation a column on reconfigurable platform (FPGAs). A novel hardware/software co-design strategy is devised and functionality tested in context speech application. An overall accuracy 98% was achieved with fixed-point technique comparison 100% floating-point software implementation.
coventry.ac.uk
sci-hub.se 参考文章(5)
Arfan Ghani, T. Martin McGinnity, Liam P. Maguire, Jim Harkin, Neuro-inspired Speech Recognition with Recurrent Spiking Neurons international conference on artificial neural networks. pp. 513- 522 ,(2008) , 10.1007/978-3-540-87536-9_53
Wolfgang Maass, Christopher M. Bishop, Pulsed neural networks ,(1998)
L.P. Maguire, T.M. McGinnity, B. Glackin, A. Ghani, A. Belatreche, J. Harkin, Challenges for large-scale implementations of spiking neural networks on FPGAs Neurocomputing. ,vol. 71, pp. 13- 29 ,(2007) , 10.1016/J.NEUCOM.2006.11.029
George R. Doddington, Thomas B. Schalk, Computers: Speech recognition: Turning theory to practice: New ICs have brought the requisite computer power to speech technology; an evaluation of equipment shows where it stands today IEEE Spectrum. ,vol. 18, pp. 26- 32 ,(1981) , 10.1109/MSPEC.1981.6369809
Wolfgang Maass, Thomas Natschläger, Henry Markram, Real-time computing without stable states: a new framework for neural computation based on perturbations Neural Computation. ,vol. 14, pp. 2531- 2560 ,(2002) , 10.1162/089976602760407955