MO-OTA based recurrent neural network for solving simultaneous linear equations

Author

Ansari, Mohd Samar ; Rahman, Syed Atiqur

Author_Institution

Dept. of Electron. Eng., A.M.U., Aligarh, India

fYear

2011

fDate

17-19 Dec. 2011

Firstpage

192

Lastpage

195

Abstract

A non-linear feedback neural network based CMOS compatible circuit to solve a system of simultaneous linear equations is presented. The circuit has an associated transcendental energy function that ensures fast convergence to the solution. The use of multi-output OTAs ensures that synaptic weight resistance are eliminated thereby reducing the circuit complexity over existing schemes. PSPICE simulation results are presented for two chosen sets of equations and are found to agree with the algebraic solutions.

Keywords

CMOS analogue integrated circuits; circuit complexity; linear algebra; operational amplifiers; recurrent neural nets; CMOS-compatible circuit; MO-OTA; PSPICE simulation; algebraic solutions; circuit complexity; multioutput OTA; nonlinear feedback neural network; operational transconductance amplifier; recurrent neural network; simultaneous linear equations; synaptic weight resistance; transcendental energy function; Biological neural networks; Equations; Integrated circuit modeling; Mathematical model; Neurons; Simulation; Transconductance; Linear algebra; Linear equations; Multi-output OTA; Neural network applications; Neural network hardware; Non-linear circuits;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia, Signal Processing and Communication Technologies (IMPACT), 2011 International Conference on

Conference_Location

Aligarh

Print_ISBN

978-1-4577-1105-3

Type

conf

DOI

10.1109/MSPCT.2011.6150472

Filename

6150472