Efficient Training Method for Memristor-Based Array Using 1T1M Synapse
- 2 February 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 70 (7) , 2410-2414
Abstract
In this brief, an efficient training method for memristor-based array (crossbar) with one transistor and one memristor (1T1M) synapse is proposed, which enables parallel update of memristor-based arrays trained by stochastic gradient descent within two steps. Voltage ThrEshold Adaptive Memristor (VTEAM) model is utilized to describe memristor characteristics for simulations. On this basis, circuit parameters optimization method compensating the asymmetric and nonlinear weight update is provided for better training results. The effectiveness of proposed training method is evaluated on OR, AND functions and digit recognition task. Simulation results demonstrate the robustness of proposed training method to electrical noise and imperfections of memristors.Keywords
Funding Information
- Natural Science Foundation of China (62271349, 61874104, 61601309)
- Natural Science Foundation of Shenzhen Municipality (JCYJ20160422093217170)
- State Grid Shandong electric power company science and technology project (520601220009)
This publication has 22 references indexed in Scilit:
- TIME2017
- Face classification using electronic synapsesNature Communications, 2017
- PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning2017
- A fully analog memristor-based neural network with online gradient training2016
- Efficient training algorithms for neural networks based on memristive crossbar circuits2015
- VTEAM: A General Model for Voltage-Controlled MemristorsIEEE Transactions on Circuits and Systems II: Express Briefs, 2015
- Memristor-Based Multilayer Neural Networks With Online Gradient Descent TrainingIEEE Transactions on Neural Networks and Learning Systems, 2015
- Memristor Multiport Readout: A Closed-Form Solution for Sneak PathsIEEE Transactions on Nanotechnology, 2014
- Memristor-Based Material Implication (IMPLY) Logic: Design Principles and MethodologiesIEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2013
- A ferroelectric memristorNature Materials, 2012