Novel training method for metal-oxide memristive synapse device to overcome trade-off between linearity and dynamic range

Jongseon Seo; Geonhui Han; Daeseok Lee

doi:10.1088/1361-6528/ac705d

Novel training method for metal-oxide memristive synapse device to overcome trade-off between linearity and dynamic range

Nanotechnology. 2022 Jun 15;33(36). doi: 10.1088/1361-6528/ac705d.

Authors

Jongseon Seo¹, Geonhui Han¹, Daeseok Lee¹

Affiliation

¹ Department of Electronic Materials Engineering, Kwangwoon University, Seoul 01897, Republic of Korea.

PMID: 35580561
DOI: 10.1088/1361-6528/ac705d

Abstract

Synapse devices are essential for the hardware implementation of neuromorphic computing systems. However, it is difficult to realize ideal synapse devices because of issues such as nonlinear conductance change (linearity) and a small number of conductance states (dynamic range). In this study, the correlation between the linearity and dynamic range was investigated. Consequently, we found a trade-off relationship between the linearity and dynamic range and proposed a novel training method to overcome this trade-off.

Keywords: carry method; dynamic range; linearity; neuromorphic system; synapse device; trade-off relation.