A Comparison of a Hardware and a Software Integrate and Fire Neural Network for Clustering Onsets in Cochlear Filtered Sound

Citation

Smith L, Glover MA & Hamilton A (1998) A Comparison of a Hardware and a Software Integrate and Fire Neural Network for Clustering Onsets in Cochlear Filtered Sound. In: Proceedings of the 1998 IEEE Signal Processing Society Workshop Neural Networks for Signal Processing VIII, 1998. 1998 IEEE Signal Processing Society Workshop Neural Networks for Signal Processing VIII, Cambridge, 31.08.1998-02.09.1998. Los Alamitos, CA, USA: IEEE, pp. 516-523. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=710682&refinements%3D4281615493%26sortType%3Dasc_p_Sequence%26filter%3DAND%28p_IS_Number%3A15338%29; https://doi.org/10.1109/NNSP.1998.710682

Abstract
Onset clustering (which we use as part of a system for sound segmentation) uses integrate-and-fire neurons to perform across spectrum and across time clustering of increases in sound intensity in different parts of the spectrum. We show that a network of recently developed analogue VLSI integrate-and-fire neurons can perform this task in real-time, and compare its performance with a simulated network

People

Professor Leslie Smith

Emeritus Professor, Computing Science