DocumentCode
352912
Title
NESP2: a low power analog neural signal processor with analog weight storage
Author
Costa, Mario ; Palmisano, Davide ; Pasero, Eros
Author_Institution
Dipartimento di Elettronica, Politecnico di Torino, Italy
Volume
4
fYear
2000
fDate
2000
Firstpage
51
Abstract
Analog artificial neural networks (ANN) could be the core of an “intelligent” signal processor, with the today used digital processing replaced by a raw “data driven” methodology. Characteristic of this approach is: analog input/output: signals don´t need A/D and D/A converters; speed: an analog system can be faster than a digital or a mixed-mode one; effectiveness: ANN already demonstrated their power in many applications; low power: analog circuits can save power. NESP2 is a neural signal processor which offers the above characteristics and is based on a traditional, available and not expensive double polysilicon double metal commercial VLSI process
Keywords
VLSI; analogue integrated circuits; analogue processing circuits; low-power electronics; neural chips; ANN; NESP2; analog I/O; analog artificial neural networks; analog input/output; analog weight storage; data driven methodology; double polysilicon double metal commercial VLSI process; intelligent signal processor; low-power analog neural signal processor; Analog memory; Artificial neural networks; Integrated circuit reliability; Integrated circuit technology; Intelligent sensors; Neurons; Nonvolatile memory; Shape control; Signal processing; Voltage;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location
Como
ISSN
1098-7576
Print_ISBN
0-7695-0619-4
Type
conf
DOI
10.1109/IJCNN.2000.860748
Filename
860748
Link To Document