A technical paper titled “ReMeCo: Reliable Memristor-Based in-Memory Neuromorphic Computation” was published by researchers at Eindhoven University of Technology, University of Tehran, and USC.
Abstract:
“Memristor-based in-memory neuromorphic computing systems promise a highly efficient implementation of vector-matrix multiplications, commonly used in artificial neural networks (ANNs). However, the immature fabrication process of memristors and circuit level limitations, i.e., stuck-at-fault (SAF), IR-drop, and device-to-device (D2D) variation, degrade the reliability of these platforms and thus impede their wide deployment. In this paper, we present ReMeCo, a redundancy-based reliability improvement framework. It addresses the non-idealities while constraining the induced overhead. It achieves this by performing a sensitivity analysis on ANN. With the acquired insight, ReMeCo avoids the redundant calculation of least sensitive neurons and layers. ReMeCo uses a heuristic approach to find the balance between recovered accuracy and imposed overhead. ReMeCo further decreases hardware redundancy by exploiting the bit-slicing technique. In addition, the framework employs the ensemble averaging method at the output of every ANN layer to incorporate the redundant neurons. The efficacy of the ReMeCo is assessed using two well-known ANN models, i.e., LeNet, and AlexNet, running the MNIST and CIFAR10 datasets. Our results show 98.5% accuracy recovery with roughly 4% redundancy which is more than 20× lower than the state-of-the-art.”
Find the technical paper here. Published Jan. 2o23.
Ali BanaGozar, Seyed Hossein Hashemi Shadmehri, Sander Stuijk, Mehdi>
Kamal, Ali Afzali-Kusha, and Henk Corporaal. 2023. ReMeCo: Reliable
memristor-based in-memory neuromorphic computation. . In 28th Asia and
South Pacific Design Automation Conference (ASPDAC ’23), January 16–19,
2023, Tokyo, Japan. ACM, New York, NY, USA, 6 pages. https://doi.org/10.
1145/3566097.3567889
Leave a Reply