Enhance the robustness to time dependent variability of ReRAM-based neuromorphic computing systems with regularization and 2R synapse

TitleEnhance the robustness to time dependent variability of ReRAM-based neuromorphic computing systems with regularization and 2R synapse
Publication TypeConference Paper
Year of Publication2019
AuthorsQ Zheng, J Kang, Z Wang, Y Cai, R Huang, B Li, Y Chen, and H Li
Conference NameProceedings Ieee International Symposium on Circuits and Systems
Date Published01/2019
Abstract

Time Dependent Variability (TDV) is one of the major concerns in implementing a Neuromorphic Computing System (NCS) with Resistive Random Access Memory (ReRAM). In this work, we propose a variation-distribution aware training algorithm to enhance the robustness of NCS to TDV without incurring extra hardware overhead by leveraging algorithm-level regularization and hardware-level 2R synapse structure. Simulation results on image recognition tasks show that our method improves the system accuracy by up to ~4% and ~10% under the worst-case TDV condition for MNIST and CIFAR-10, respectively. Detailed analysis also shows that our method allows the NCS to use synapses with higher resistance than conventional design for the same accuracy requirement, introducing potential energy saving.

DOI10.1109/ISCAS.2019.8702756