A submicron analog neural network with an adjustable-level output unit

Author

Abutalebi, A.H. ; Fakhraie, S.M.

Author_Institution

Dept. of Electr. & Comput. Eng., Tehran Univ., Iran

fYear

1998

fDate

6/20/1905 12:00:00 AM

Firstpage

294

Lastpage

297

Abstract

A submicron feedforward analog neural network is described. This network uses submicron Gilbert multipliers for its synapses and a novel circuit based on the current-comparator circuit for its neuron. The XOR problem is solved by this network to demonstrate the capability of implementing multi-layer networks. The network is designed in a 0.5 μm technology. HSPICE simulation shows the validity of the operation of the network

Keywords

CMOS analogue integrated circuits; SPICE; analogue multipliers; circuit simulation; current comparators; feedforward neural nets; integrated circuit design; neural chips; 0.5 mum; CMOS technology; HSPICE simulation; XOR problem; adjustable-level output unit; current-comparator circuit; multi-layer networks; neuron; submicron Gilbert multipliers; submicron analog neural network; submicron feedforward analog neural network; synapses; Artificial neural networks; Biomedical engineering; CMOS technology; Circuit simulation; Multi-layer neural network; Neural network hardware; Neural networks; Neurons; Parallel processing; Systems engineering and theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Microelectronics, 1998. ICM '98. Proceedings of the Tenth International Conference on

Conference_Location

Monastir

Print_ISBN

0-7803-4969-5

Type

conf

DOI

10.1109/ICM.1998.825622

Filename

825622