DocumentCode :
3210917
Title :
Current Mode Analog Kohonen Neural Network
Author :
Talaska, M.S.T. ; Dlugosz, R. ; Wojtyna, R.
Author_Institution :
Univ. of Technol. & Life Sci., Bydgoszcz
fYear :
2007
fDate :
21-23 June 2007
Firstpage :
250
Lastpage :
255
Abstract :
In this paper we present Matlab analysis as well as CMOS implementation of an analog current mode Kohonen neural network (KNN). The presented KNN has been realized using several building blocks proposed earlier by the authors, such as: binary tree winner take all circuit, Euclidean distance calculation circuit, adaptive weights change mechanism. The example network contains four neurons, each of them having three weights. There are three input signals applied, which can be currents or voltages converted just at the beginning into currents. The network operates with the clock frequency of 20 MHz, dissipating 1.5 mW of power from 1.5 V supply voltage. For lower operation frequencies power dissipation can be reduced.
Keywords :
CMOS analogue integrated circuits; neural nets; CMOS implementation; Matlab analysis; current mode analog Kohonen neural network; Biological neural networks; CMOS analog integrated circuits; CMOS technology; Circuit simulation; Frequency; Neural networks; Neurons; Power dissipation; Signal processing algorithms; Voltage; Analog CMOS circuits; Kohonen´s neural networks; Winner takes all competitive learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Mixed Design of Integrated Circuits and Systems, 2007. MIXDES '07. 14th International Conference on
Conference_Location :
Ciechocinek
Print_ISBN :
83-922632-9-4
Electronic_ISBN :
83-922632-9-4
Type :
conf
DOI :
10.1109/MIXDES.2007.4286160
Filename :
4286160
Link To Document :
بازگشت