3D Integrable W/SiN x/n-Si/p-Si 1D1R Unipolar Resistive Random Access Memory Synapse for Suppressing Reverse Leakage in Spiking Neural Network

Chae Soo Kim; Taehyung Kim; Kyung Kyu Min; Sungjun Kim; Byung-Gook Park

doi:10.1166/jnn.2020.17806

3D Integrable W/SiN x/n-Si/p-Si 1D1R Unipolar Resistive Random Access Memory Synapse for Suppressing Reverse Leakage in Spiking Neural Network

J Nanosci Nanotechnol. 2020 Aug 1;20(8):4735-4739. doi: 10.1166/jnn.2020.17806.

Authors

Chae Soo Kim¹, Taehyung Kim¹, Kyung Kyu Min¹, Sungjun Kim², Byung-Gook Park¹

Affiliations

¹ Department of Electrical and Computer Engineering, Seoul National University, Seoul 08826, Republic of Korea.
² School of Electronics Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea.

PMID: 32126649
DOI: 10.1166/jnn.2020.17806

Abstract

In this paper, we pose reverse leakage current issue which occurs when resistive random access memory (RRAM) is used as synapse for spiking neural networks (SNNs). To prevent this problem, 1 diode-1 RRAM (1D1R) synapse is suggested and simulated to examine their current rectifying chracteristics, Furthermore, high density of 1 K 3D 1D1R synapse array structure and its process flow are proposed.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Neural Networks, Computer*
Synapses*