학술논문
Noise-Resilient DNN: Tolerating Noise in PCM-Based AI Accelerators via Noise-Aware Training
Document Type
Periodical
Author
Source
IEEE Transactions on Electron Devices IEEE Trans. Electron Devices Electron Devices, IEEE Transactions on. 68(9):4356-4362 Sep, 2021
Subject
Language
ISSN
0018-9383
1557-9646
1557-9646
Abstract
Phase change memory (PCM)-based “Analog-AI” accelerators are gaining importance for inference in edge applications due to the energy efficiency offered by in-memory computing. Nevertheless, noise sources inherent to PCM devices cause inaccuracies in the deep neural network (DNN) weight values. Such inaccuracies can lead to severe degradation in model accuracy. To address this, we propose two techniques to improve noise resiliency of DNNs: 1) drift regularization (DR) and 2) multiplicative noise training (MNT). We evaluate convolutional networks trained on image classification and recurrent neural networks trained on language modeling and show that our techniques improve model accuracy by up to 12% over one month.