Title :
Low-power macro-cells for pulse code arithmetic
Author :
Naess, S. ; Lande, Tor Suerre
Author_Institution :
Dept. of Inf., Oslo Univ., Norway
Abstract :
This paper presents low-power macro-cells for pulse code arithmetic in neuromorphic systems based on stochastic pulse coded signals. By using a dynamic error-correction technique, square-root extraction can be performed with good accuracy. The cells have been fabricated in a 2 μ process, and are presented along with real-world measurement results, showing the feasibility of the methods
Keywords :
cellular neural nets; digital arithmetic; error correction; pulse code modulation; stochastic systems; 2 mum; dynamic error-correction; feasibility; low-power macro-cells; neuromorphic systems; pulse code arithmetic; square-root extraction; stochastic pulse coded signals; Arithmetic; Biology computing; Circuits; Computer vision; Energy consumption; Informatics; Neuromorphics; Signal representations; Stochastic processes; Stochastic systems;
Conference_Titel :
Electronics, Circuits and Systems, 1998 IEEE International Conference on
Conference_Location :
Lisboa
Print_ISBN :
0-7803-5008-1
DOI :
10.1109/ICECS.1998.813989
