TY - JOUR

T1 - RRAM Compact Modeling Using Physics and Machine Learning Hybridization

AU - Lin, Albert S.

AU - Liu, Po Ning

AU - Pratik, Sparsh

AU - Yang, Zheng Kai

AU - Rawat, Tejender

AU - Tseng, Tseung Yuen

N1 - Publisher Copyright:
IEEE

PY - 2022

Y1 - 2022

N2 - Machine learning (ML)-based compact model (CM) provide an alternative way in contrast to physics-based CMs. The advantages of ML CMs include the process-aware capability, expandability, improved behavioral model for a circuit block, and usability for emerging devices. On the other hand, while ML is on the rise, device physics can provide many guidelines in constructing ML CMs. Here, we propose a physics architecture in ML CMs for resistive random access memory (RRAM). The results show that the physics-assisted architecture enables simpler ML models in reference to our previous work of long short-term memory (LSTM)-based RRAM CMs. We found that the discrete state variable with classification is the best model to describe the RRAM set/reset scenario in multistep prediction problems. For the discrete and continuous state variables, the root mean square error (RMSE) on test data is 0.000125 and 0.000119, respectively. In addition, we demonstrate that the transient behavior of set/reset changes can be easily incorporated into the proposed model. Finally, the Verilog-A and HSPICE on a 1T1R cell have also been shown to prove the model feasibility. We suggest that the uniform framework with hybridization in physics and ML should be the most efficient way in future compact device modeling. The code is available at https://github.com/albertlin11/RRAMunif.

AB - Machine learning (ML)-based compact model (CM) provide an alternative way in contrast to physics-based CMs. The advantages of ML CMs include the process-aware capability, expandability, improved behavioral model for a circuit block, and usability for emerging devices. On the other hand, while ML is on the rise, device physics can provide many guidelines in constructing ML CMs. Here, we propose a physics architecture in ML CMs for resistive random access memory (RRAM). The results show that the physics-assisted architecture enables simpler ML models in reference to our previous work of long short-term memory (LSTM)-based RRAM CMs. We found that the discrete state variable with classification is the best model to describe the RRAM set/reset scenario in multistep prediction problems. For the discrete and continuous state variables, the root mean square error (RMSE) on test data is 0.000125 and 0.000119, respectively. In addition, we demonstrate that the transient behavior of set/reset changes can be easily incorporated into the proposed model. Finally, the Verilog-A and HSPICE on a 1T1R cell have also been shown to prove the model feasibility. We suggest that the uniform framework with hybridization in physics and ML should be the most efficient way in future compact device modeling. The code is available at https://github.com/albertlin11/RRAMunif.

KW - Compact device modeling

KW - Integrated circuit modeling

KW - machine learning (ML)

KW - Mathematical models

KW - Physics

KW - Predictive models

KW - resistive random access memory (RRAM)

KW - Semiconductor device modeling

KW - semiconductor device physics.

KW - SPICE

KW - Voltage

UR - http://www.scopus.com/inward/record.url?scp=85126328221&partnerID=8YFLogxK

U2 - 10.1109/TED.2022.3152978

DO - 10.1109/TED.2022.3152978

M3 - Article

AN - SCOPUS:85126328221

JO - Ieee Transactions On Electron Devices

JF - Ieee Transactions On Electron Devices

SN - 0018-9383

ER -