Title :
A modular gm-C programmable CNN implementation
Author :
Lím, Drahoslav ; Moschytz, George S.
Author_Institution :
Signal & inf. Process. Lab., Fed. Inst. of Technol., Zurich, Switzerland
Abstract :
A programmable cellular neural network has been designed in a 0.8 μ CMOS technology. An arbitrarily large analog CNN can be constructed by modularly connecting `tile´ CNN chips, each with a modest number of cells. The network operates in continuous time, has a PWL output function, and the cell connections (template values) are realized as sets of switchable unit and half-unit transconductors. Matching accuracy, including matching among chips from different manufacturing runs, and operation was verified on uncoupled and coupled templates
Keywords :
CMOS analogue integrated circuits; cellular neural nets; continuous time systems; coupled circuits; neural chips; piecewise-linear techniques; CMOS technology; PWL output function; cell connections; continuous time network; coupled templates; half-unit transconductors; matching accuracy; modular gm-C circuit; programmable CNN implementation; switchable unit transconductors; template values; uncoupled templates; Algorithm design and analysis; CMOS technology; Cellular neural networks; Circuit testing; Gray-scale; Information processing; Laboratories; Parallel processing; Piecewise linear techniques; Signal processing;
Conference_Titel :
Circuits and Systems, 1998. ISCAS '98. Proceedings of the 1998 IEEE International Symposium on
Conference_Location :
Monterey, CA
Print_ISBN :
0-7803-4455-3
DOI :
10.1109/ISCAS.1998.703929
