Topology-Aware Recognition Framework Based on Ultra-High On/Off Ratio Memristors for Handwritten Digit Recognition
- 6 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Electron Device Letters
- Vol. 46 (12) , 2349-2352
Abstract
Conventional passive memristor arrays face crosstalk challenges in on-chip neuromorphic computing, while 1T1R/1S1R architectures suffer from limited scalability and area overhead. Here, we propose a topology-aware recognition framework for crosstalk-free on-chip compute-in-memory (CIM) using high-performance Pt/In2O3(Cr-doped)/W memristors. The devices demonstrate exceptional metrics: an ultra-high on/off ratio (>10⁸), retention exceeding 107 s, and endurance over 10⁵ cycles. Integrated into passive arrays, these memristors enable a novel paradigm that converts image pixel intensities into spatiotemporal pulse sequences encoding topological features (spatial brightness relationships). These features are mapped to 32 × 32 crossbar arrays, where recognition is determined by counting diagonal-activated devices—ensuring single-device activation per row/column to eliminate crosstalk. The system achieves 99.8% accuracy on MNIST and scalability to 6.59 PB (with 10% read margin), outperforming existing on-chip networks. This work bridges device innovation with algorithmic co-design, advancing energy-efficient neuromorphic hardware for pattern recognition.Keywords
Funding Information
- Natural Science Foundation of Zhejiang Province (No. LDT23F0401)
- National Natural Science Foundation of China (No.62204219)
- open research fund of Suzhou Laboratory (No.SZLAB-1208-2024-TS012)
This publication has 24 references indexed in Scilit:
- Neuromorphic Hardware for Artificial Sensory Systems: A ReviewJournal of Electronic Materials, 2025
- Resistive switching properties in ferromagnetic co-doped ZnO thin films-based memristors for neuromorphic computingJournal of Materials Science: Materials in Electronics, 2024
- Effect of chromium-doping on structure and opto-electronics properties of nanostructured indium tin oxide thin filmsApplied Physics A, 2022
- Time series classification through visual pattern recognitionJournal of King Saud University Computer and Information Sciences, 2022
- CMOS back-end-of-line compatible ferroelectric tunnel junction devicesSolid-State Electronics, 2021
- Breaking the von Neumann bottleneck: architecture-level processing-in-memory technologyScience China Information Sciences, 2021
- Hardware Implementation of Neuromorphic Computing Using Large‐Scale Memristor Crossbar ArraysAdvanced Intelligent Systems, 2020
- TFT Technology: Advancements and Opportunities for ImprovementInformation Display, 2020
- Memristive Devices and Networks for Brain‐Inspired ComputingPhysica Status Solidi (RRL) – Rapid Research Letters, 2019
- Emerging Memory Devices for Neuromorphic ComputingAdvanced Materials Technologies, 2019