Continual Learning Electrical Conduction in Resistive‐Switching‐Memory Materials. Issue 8 (2nd June 2022)

• Record Type: Journal Article
• Authors: Go, Shao‐Xiang; Wang, Qiang; Wang, Bo; Jiang, Yu; Bajalovic, Natasa; Loke, Desmond K.
• Is Part Of: Advanced theory and simulations. Volume 5:Issue 8(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-06-02
• Subjects: computational methods -- electrical properties -- incremental learning -- machine learning -- resistive memory; Science -- Simulation methods -- Periodicals; Science -- Methodology -- Periodicals; Engineering -- Simulation methods -- Periodicals; Engineering -- Methodology -- Periodicals; 507.21
• DOI: 10.1002/adts.202200226
• Languages: English
• ISSNs: 2513-0390

Abstract

Abstract: The authors apply the concept of continual learning to modeling conductive‐filament growth in resistive‐switching materials (RSM). The approach permits computation of compliance current without knowing the geometries of conductive filaments and switching behaviors. This avoids the need to retrain the entire dataset when additional compliance currents are considered and is thus ideal for resistive switching (RS) thin films, doped layers, and other material systems. Computation of compliance current is consistent with experimental data for a wide range of parameters and learning tasks and demonstrates switching behavior not captured by traditional models. Lesion calculations elucidate the brain‐inspired‐modification‐facilitated increase in compliance‐current‐computation‐accuracy. A state‐of‐the‐art performance on challenging compliance‐current learning tasks without storing data is achieved ("brain inspired replay (BIR) – gating based on internal context (Gat)" method, ≈89%; above a benchmark of ≈50% for synaptic‐intelligence (SI)/elastic‐weight‐consolidation (EWC) methods), and it provides a novel model for computing compliance current based on replay of the brain. This intuitive approach combined with a simple solver tool, allows researchers with little computation experience to perform realistic and accurate modeling. Abstract : Inspired by continual learning methods, a method is developed to evaluate compliance current in subsequent experiments without the need to store data. This method outperforms other continual learning methods such as elastic weight consolidation and synaptic intelligence when applied on the compliance current dataset. A state‐of‐the‐art result is achieved after further adding modifications to the proposed method.