Quantized current conduction in memristors and its physical model

Zhang, Yuying; Mou, Nurunnahar Islam; Pai, Pradeep; Tabib-Azar, Massood

doi:10.1109/icsens.2014.6985125

Cited by 3 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar filament growth simulations have been done before in Ref. 52 utilizing different theoretical models.…”

Section: Appendix: the Numerical Simulationssupporting

confidence: 52%

Asymmetry-induced resistive switching in Ag-Ag$_{2}$S-Ag memristors enabling a simplified atomic-scale memory design

Gubicza,

Manrique,

Pósa

et al. 2016

Preprint

View full text Add to dashboard Cite

Prevailing models of resistive switching arising from electrochemical formation of conducting filaments across solid state ionic conductors commonly attribute the observed polarity of the voltagebiased switching to the sequence of the active and inert electrodes confining the resistive switching memory cell. Here we demonstrate equivalent, stable switching behavior in metallic Ag-Ag2S-Ag nanojunctions at room temperature. Our experimental results and numerical simulations reveal that the polarity of the switchings is solely determined by the geometrical asymmetry of the electrode surfaces. By the lithographical design of a proof of principle device we demonstrate the merits of simplified fabrication of atomic-scale, robust planar Ag2S memory cells.

show abstract

“…Similar filament growth simulations have been done before in Ref. 52 utilizing different theoretical models.…”

Section: Appendix: the Numerical Simulationssupporting

confidence: 52%

Asymmetry-induced resistive switching in Ag-Ag$_{2}$S-Ag memristors enabling a simplified atomic-scale memory design

Gubicza,

Manrique,

Pósa

et al. 2016

Preprint

View full text Add to dashboard Cite

show abstract

“…On the other hand, Zhang. et al [24] discussed the effectiveness of using the quantized conductance in memristor in multi-level logics. Song.…”

Section: Introductionmentioning

confidence: 99%

“…We consider hardware constraints such as crossbar blocks pruning, conductance range, and mismatch between weight value and real devices, to achieve high accuracy and low power and small area footprint. Our proposed framework can better mitigate the inaccuracy caused by the hardware imperfection compared to only weight quantization method [24,25]. It contains memristor-based ADMM regularized optimization, masked mapping and retraining steps, which can guarantee the solution feasibility (satisfying all constraints) and provide high solution quality (maintaining test accuracy) at the same time.…”

Section: Introductionmentioning

confidence: 99%

An Ultra-Efficient Memristor-Based DNN Framework with Structured Weight Pruning and Quantization Using ADMM

Yuan

Ding

et al. 2019

2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)

View full text Add to dashboard Cite

The high computation and memory storage of large deep neural networks (DNNs) models pose intensive challenges to the conventional Von-Neumann architecture, incurring substantial data movements in the memory hierarchy. The memristor crossbar array has emerged as a promising solution to mitigate the challenges and enable low-power acceleration of DNNs. Memristor-based weight pruning and weight quantization have been seperately investigated and proven effectiveness in reducing area and power consumption compared to the original DNN model. However, there has been no systematic investigation of memristor-based neuromorphic computing (NC) systems considering both weight pruning and weight quantization. In this paper, we propose an unified and systematic memristorbased framework considering both structured weight pruning and weight quantization by incorporating alternating direction method of multipliers (ADMM) into DNNs training. We consider hardware constraints such as crossbar blocks pruning, conductance range, and mismatch between weight value and real devices, to achieve high accuracy and low power and small area footprint. Our framework is mainly integrated by three steps, i.e., memristorbased ADMM regularized optimization, masked mapping and retraining. Experimental results show that our proposed framework achieves 29.81× (20.88×) weight compression ratio, with 98.38% (96.96%) and 98.29% (97.47%) power and area reduction on VGG-16 (ResNet-18) network where only have 0.5% (0.76%) accuracy loss, compared to the original DNN models. We share our models at anonymous link http://bit.ly/2Jp5LHJ.

show abstract

An Ultra-Efficient Memristor-Based DNN Framework with Structured Weight Pruning and Quantization Using ADMM

Yuan

Ding

et al. 2019

Preprint

View full text Add to dashboard Cite

Quantized current conduction in memristors and its physical model

Cited by 3 publications

References 12 publications

Asymmetry-induced resistive switching in Ag-Ag$_{2}$S-Ag memristors enabling a simplified atomic-scale memory design

Asymmetry-induced resistive switching in Ag-Ag$_{2}$S-Ag memristors enabling a simplified atomic-scale memory design

An Ultra-Efficient Memristor-Based DNN Framework with Structured Weight Pruning and Quantization Using ADMM

An Ultra-Efficient Memristor-Based DNN Framework with Structured Weight Pruning and Quantization Using ADMM

Contact Info

Product

Resources

About