Robust Brain-Inspired Computing: On the Reliability of Spiking Neural Network Using Emerging Non-Volatile Synapses
Authors:
- 1 March 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
A spiking neural network (SNN) with non-volatile memory synapses can facilitate an ideal analog approach with low power consumption for intelligent applications. However, reliability issues would arise due to the characteristics of Non-Volatile Memory synapses operating under the limited size of a neural circuit component called membrane capacitor, resulting in low precision MAC. Through a simulation study, we identified several important criteria of the memory synapses that affect performance of the SNN for the membrane capacitor size of 1pF. (1) The required ON-OFF ratio of synapse needs to be >1000 to preserve classification accuracy. (2) Low on-current Ion (<10uA) is preferred for low power. (3) The variation and error of Ion should be lower than +/- 10% of mean value.Keywords
This publication has 14 references indexed in Scilit:
- Low power and high uniformity of HfOx-based RRAM via tip-enhanced electric fieldsScience China Information Sciences, 2019
- A System-Level Simulator for RRAM-Based Neuromorphic Computing ChipsACM Transactions on Architecture and Code Optimization, 2018
- HEIF: Highly Efficient Stochastic Computing-Based Inference Framework for Deep Neural NetworksIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018
- A Novel 3D AND-type NVM Architecture Capable of High-density, Low-power In-Memory Sum-of-Product Computation for Artificial Intelligence Application2018
- Reliability perspective of resistive synaptic devices on the neuromorphic system performance2018
- A 65nm 1Mb nonvolatile computing-in-memory ReRAM macro with sub-16ns multiply-and-accumulate for binary DNN AI edge processors2018
- Loihi: A Neuromorphic Manycore Processor with On-Chip LearningIEEE Micro, 2018
- Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing2015
- Spiking Neural Network with RRAM: Can We Use It for Real-World Application?2015
- Multi-level 40nm WOX resistive memory with excellent reliability2011