Majority neuron circuit having large fan-in with non-volatile synaptic weight

Author

Akima, H. ; Katayama, Yasunao ; Nakajima, Kensuke ; Sakuraba, Masao ; Sato, Seiki

Author_Institution

Res. Inst. of Electr. Commun., Tohoku Univ., Sendai, Japan

fYear

2014

fDate

6-11 July 2014

Firstpage

4266

Lastpage

4271

Abstract

We present a design of a majority neuron circuit with non-volatile synaptic weights. It is based on an analog majority circuit composed of controlled current inverters (CCIs). The proposed circuit is immune to device parameter fluctuations, and its fan-in is estimated about 1000. Synaptic weights are realized on the neuron circuit by adding variable resistors. We consider a design of a non-volatile synaptic weight by using a three-terminal magnetic domain-wall motion (DWM) device. The operation of a fully connected recurrent neural network composed of the proposed circuits has been confirmed by SPICE simulation.

Keywords

recurrent neural nets; resistors; DWM device; SPICE simulation; analog majority circuit; controlled current inverters; fan-in; fully connected recurrent neural network; majority neuron circuit; nonvolatile synaptic weights; three-terminal magnetic domain-wall motion; variable resistors; Artificial neural networks; Inverters; MOSFET; Magnetic tunneling; Neurons; Resistors; Threshold voltage;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks (IJCNN), 2014 International Joint Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4799-6627-1

Type

conf

DOI

10.1109/IJCNN.2014.6889766

Filename

6889766