Wordline Input Bias Scheme for Neural Network Implementation in 3D-NAND Flash

Wordline Input Bias Scheme for Neural Network Implementation in 3D-NAND Flash

In this study, we propose a neuromorphic computing system based on a 3D-NAND flash architecture that utilizes analog input voltages applied through wordlines (WLs). The approach leverages the velocity saturation effect in short-channel MOSFETs, which enables a linear increase in drain current with r...

Full description

Saved in:
Bibliographic Details
Main Authors: Hwiho Hwang, Gyeonghae Kim, Dayeon Yu, Hyungjin Kim
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Biomimetics
Subjects:
computing-in-memory (CIM)
3D-NAND architecture
neuromorphic computing
vector-matrix multiplication (VMM)
velocity saturation
Online Access:https://www.mdpi.com/2313-7673/10/5/318
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this study, we propose a neuromorphic computing system based on a 3D-NAND flash architecture that utilizes analog input voltages applied through wordlines (WLs). The approach leverages the velocity saturation effect in short-channel MOSFETs, which enables a linear increase in drain current with respect to gate voltage in the saturation region. A NAND flash array with a TANOS (TiN/Al<sub>2</sub>O<sub>3</sub>/Si<sub>3</sub>N<sub>4</sub>/SiO<sub>2</sub>/poly-Si) gate stack was fabricated, and its electrical and reliability characteristics were evaluated. Output characteristics of short-channel (<i>L</i> = 1 µm) and long-channel (<i>L</i> = 50 µm) devices were compared, confirming the linear behavior of short-channel devices due to velocity saturation. In the proposed system, analog WL voltages serve as inputs, and the summed bitline (BL) currents represent the outputs. Each synaptic weight is implemented using two paired devices, and each WL layer corresponds to a fully connected (FC) layer, enabling efficient vector-matrix multiplication (VMM). MNIST pattern recognition is conducted, demonstrated only a 0.32% accuracy drop for the short-channel device compared to the ideal linear case, and 0.95% degradation under 0.5 V threshold variation, while maintaining robustness. These results highlight the strong potential of 3D-NAND flash memory, which offers high integration density and technological maturity, for neuromorphic computing applications.
ISSN:2313-7673

Similar Items