Title :
Hybrid-control of synapse circuits for programmable cellular neural networks
Author :
Espejo, S. ; Dominguez-Castro, R. ; Carmona, R. ; Rodriguez-Vazquez, Angel
Author_Institution :
Centro Nacional de Microelectron., Seville Univ., Spain
Abstract :
This paper describes a hybrid weight-control strategy for VLSI realizations of programmable Cellular Neural Networks (CNNs), based on auto-tuning of analog control signals to digitally specified values. The approach merges the advantages of digital and analog programmability, achieving low areas and reduced number of control lines, simplifying the control and storage of weight values, and eliminating their dependency on global process-parameter variations
Keywords :
VLSI; cellular neural nets; circuit tuning; neural chips; VLSI realizations; analog control signals; analog programmability; auto-tuning; control lines; digitally specified values; global process-parameter variations; hybrid weight-control strategy; programmable cellular neural networks; synapse circuits; weight values; Cellular neural networks; Circuits; Computer applications; Design optimization; Digital control; Electronic mail; Joining processes; Signal processing; Very large scale integration; Voltage;
Conference_Titel :
Circuits and Systems, 1996. ISCAS '96., Connecting the World., 1996 IEEE International Symposium on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3073-0
DOI :
10.1109/ISCAS.1996.541644
