Indexed by:Journal paper First Author:Danzhe Song Correspondence Author:Xingsheng Wang Co-author:Fan Yang,Chengxu Wang,Nan Li,Pinfeng Jiang,Bin Gao,Xiangshui Miao Journal:IEEE Electron Device Letters Included Journals:SCI、EI Document Type:J Volume:44 Issue:8 Page Number:1280-1283 Key Words:Memristor array, line resistance, IR-Drop, neural network, activation function DOI number:10.1109/LED.2023.3285916 Date of Publication:2023-06-14 Abstract:The line resistance (LR) in a large-scale memristor crossbar array can cause serious IR-drop problem, degrading the hardware deployment capability of neural networks (NNs). In this work, two innovation schemes from the level of software are proposed to mitigate the hardware IR-drop problem by intentionally modulating the NN activation function before deploying. The methods are evaluated over typical activation functions and various line resistances on MLP and LeNet-5 for MNIST recognition. Results show the methods can significantly improve the tolerance of NNs to IR-drop and recover the accuracy in some extent. The methods require no extra hardware overhead and reduce the complexity of peripheral circuits, which make them more achievable and attractive. Links to published journals:https://ieeexplore.ieee.org/document/10152462