paper-with-me

홈 › Papers

Efficient Calibration for RRAM-based In-Memory Computing using DoRA

2025-04-02 · Weirong Dong, Kai Zhou, Zhen Kong, Quan Cheng, Junkai Huang, Zhengke Yang, Masanori Hashimoto, Longyang Lin

Resistive In-Memory Computing (RIMC) offers ultra-efficient computation for edge AI but faces accuracy degradation due to RRAM conductance drift over time. Traditional retraining methods are limited by RRAM's high energy consumption, write latency, and endurance constraints. We propose a DoRA-based calibration framework that restores accuracy by compensating influential weights with minimal calibration parameters stored in SRAM, leaving RRAM weights untouched. This eliminates in-field RRAM writes, ensuring energy-efficient, fast, and reliable calibration. Experiments on RIMC-based ResNet50 (ImageNet-1K) demonstrate 69.53% accuracy restoration using just 10 calibration samples while updating only 2.34% of parameters.

📄 PDF Abstract BibTeX arXiv:2504.03763

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

High-Throughput In-Memory Computing for Binary Deep Neural Networks with Monolithically Integrated RRAM and 90nm CMOS

2019-09-16 · Shihui Yin, Xiaoyu Sun, Shimeng Yu, Jae-sun Seo

Deep learning hardware designs have been bottlenecked by conventional memories such as SRAM due to density, leakage and parallel computing challenges. Resistive devices can address the density and volatility issues, but …

Edge-computing

The Combination of Metal Oxides as Oxide Layers for RRAM and Artificial Intelligence

2023-04-29 · Sun Hanyu

Resistive random-access memory (RRAM) is a promising candidate for next-generation memory devices due to its high speed, low power consumption, and excellent scalability. Metal oxides are commonly used as the oxide layer…

Dielectric Constant

Multi-level, Forming Free, Bulk Switching Trilayer RRAM for Neuromorphic Computing at the Edge

2023-10-20 · Jaeseoung Park, Ashwani Kumar, Yucheng Zhou, Sangheon Oh 외

Resistive memory-based reconfigurable systems constructed by CMOS-RRAM integration hold great promise for low energy and high throughput neuromorphic computing. However, most RRAM technologies relying on filamentary swit…

Autonomous Navigation

Realizing Ultra-Fast and Energy-Efficient Baseband Processing Using Analogue Resistive Switching Memory

2022-05-07 · Qunsong Zeng, Jiawei Liu, Jun Lan, Yi Gong 외

To support emerging applications ranging from holographic communications to extended reality, next-generation mobile wireless communication systems require ultra-fast and energy-efficient (UFEE) baseband processors. Trad…

Realizing In-Memory Baseband Processing for Ultra-Fast and Energy-Efficient 6G

2023-08-19 · Qunsong Zeng, Jiawei Liu, Mingrui Jiang, Jun Lan 외

To support emerging applications ranging from holographic communications to extended reality, next-generation mobile wireless communication systems require ultra-fast and energy-efficient baseband processors. Traditional…