Alternate Pulse Scheme in a Hardware Neural Network for Reducing the Influence of Asymmetry on Synaptic Weight Updating

Citations

WEB OF SCIENCE

6
Citations

SCOPUS

6

초록

Recently, researchers have been paying more attention to hardware neural networks with memory devices acting as synapses due to their small area and low power consumption. We prefer to use a phase-change memory (PCM) device as a synapse due to its excellent synapse-like properties. However, due to the programming mechanism of PCMs, the asymmetric characteristic of the PCM between partially set and partially reset is severe. In this paper, we proposed an alternate pulse scheme (APS) to reduce the influence of the asymmetry between long-term potentiation and long-term depression operations.

키워드

Phase-change memoryPCMneural networkfeature extractionneuronsynapseFeature extractionLow power electronicsNeural networksNeuronsPulse code modulationPhase change memoryAsymmetric characteristicHardware neural networksLong term depressionLong-term potentiationsLow-power consumptionPhase change memory (pcm)Programming mechanismSynapse
제목
Alternate Pulse Scheme in a Hardware Neural Network for Reducing the Influence of Asymmetry on Synaptic Weight Updating
저자
Li, ChengAn, JunseopKweon, Jun YoungSong, Yun Heub
DOI
10.5573/JSTS.2020.20.1.119
발행일
2020-02
유형
Article
저널명
JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE
20
1
페이지
119 ~ 126