A neuromorphic cross-correlation chip

The cross-correlation and auto-correlation operations are important in many signal processing tasks. Often these operations are resource intensive or limited by noise in low-power systems. In this paper we present the design and measured results of an analogue integrated circuit (IC) that performs cross-correlations using a neuromorphic algorithm.

[1]  B. L. Dokic.  CMOS Schmidt triggers , 1984 .

[2]  Ralph Etienne-Cummings,et al.  Implementing a neuromorphic cross-correlation engine with silicon neurons , 2008, 2008 IEEE International Symposium on Circuits and Systems.

[3]  Tobi Delbrück,et al.  Bias Current Generators with Wide Dynamic Range , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[4]  J. Tapson,et al.  A Scalable Architecture for Event-Based Cross-Correlation , 2007, 2007 IEEE Biomedical Circuits and Systems Conference.

[5]  Rahul Sarpeshkar,et al.  A Low-Power Wide-Linear-Range Transconductance Amplifier , 1997 .

[6]  Ralph Etienne-Cummings,et al.  A Simple Neural Cross-Correlation Engine , 2007, 2007 IEEE International Symposium on Circuits and Systems.

[7]  J. Tapson.  Autocorrelation properties of single neurons , 1998, Proceedings of the 1998 South African Symposium on Communications and Signal Processing-COMSIG '98 (Cat. No. 98EX214).