Title :
Optical sensor integrated CNN for real-time computational applications
Author :
Karahaliloglu, Koray ; Gans, Patrick ; Schemm, Nathan ; Balkir, Sina
Author_Institution :
Dept. of Electr. & Comput. Eng., Virginia Commonwealth Univ., Richmond, VA
Abstract :
A previously implemented CNN layer based on a bio-inspired system model is integrated with optical sensors comprised of PN type photodiodes and the design is fabricated in CMOS technology. The implemented test chip is measured and obtained results are presented. The sensor integration marks a new step in prototyping of this system in CMOS, which allows the cell states to be programmed via light interactions, rather than successive state programming procedure which was utilized previously. It is shown that the cell input states in the network can be successfully introduced via exposure of the 2D array to a light source. The followed custom design methods and this remarkably compatible sensor integration can lead to compact on-chip solutions for real-time high performance applications, including but not limited to certain types of image processing
Keywords :
CMOS integrated circuits; integrated optoelectronics; neural nets; optical sensors; photodiodes; 2D array; CMOS technology; PN type photodiodes; bioinspired system; image processing; integrated cellular neural network; optical sensor; real-time computation; test chip; CMOS technology; Cellular neural networks; Computer applications; Optical computing; Optical design; Optical sensors; Photodiodes; Semiconductor device measurement; Semiconductor device modeling; Testing;
Conference_Titel :
Circuits and Systems, 2006. ISCAS 2006. Proceedings. 2006 IEEE International Symposium on
Conference_Location :
Island of Kos
Print_ISBN :
0-7803-9389-9
DOI :
10.1109/ISCAS.2006.1693439