Explainable Model Prediction of Memristor
System level simulation of neuro-memristive circuits under variability are complex and follow a black-box neural network approach. In realistic hardware, they are often difficult to cross-check for accuracy and reproducible results. The accurate memristor model prediction becomes critical to deciphe...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of the Industrial Electronics Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10631696/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526351317696512 |
|---|---|
| author | Sruthi Pallathuvalappil Rahul Kottappuzhackal Alex James |
| author_facet | Sruthi Pallathuvalappil Rahul Kottappuzhackal Alex James |
| author_sort | Sruthi Pallathuvalappil |
| collection | DOAJ |
| description | System level simulation of neuro-memristive circuits under variability are complex and follow a black-box neural network approach. In realistic hardware, they are often difficult to cross-check for accuracy and reproducible results. The accurate memristor model prediction becomes critical to decipher the overall circuit function in a wide range of nonideal and practical conditions. In most neuro-memristive systems, crossbar configuration is essential for implementing multiply and accumulate calculations, that form the primary unit for neural network implementations. Predicting the specific memristor model that best fits the crossbar simulations to make it explainable is an open challenge that is solved in this article. As the size of the crossbar increases the cross-validation becomes even more challenging. This article proposes predicting the memristor device under test by automatically evaluating the <italic>I–V</italic> behavior using random forest and extreme gradient boosting algorithms. Starting with a single memristor model, the prediction approach is extended to memristor crossbar-based circuits explainable. The performance of both algorithms is analyzed based on precision, recall, f1-score, and support. The accuracy, macro average, and weighted average of both algorithms at different operational frequencies are explored. |
| format | Article |
| id | doaj-art-7494e65af9924c0bb5ce50e2e72edd2f |
| institution | Kabale University |
| issn | 2644-1284 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Industrial Electronics Society |
| spelling | doaj-art-7494e65af9924c0bb5ce50e2e72edd2f2025-01-17T00:00:44ZengIEEEIEEE Open Journal of the Industrial Electronics Society2644-12842024-01-01583684610.1109/OJIES.2024.344057810631696Explainable Model Prediction of MemristorSruthi Pallathuvalappil0https://orcid.org/0000-0002-7447-2495Rahul Kottappuzhackal1Alex James2https://orcid.org/0000-0001-5655-1213School of Electronic Systems and Automation, Digital University Kerala, Trivandrum, Kerala, IndiaSchool of Electronic Systems and Automation, Digital University Kerala, Trivandrum, Kerala, IndiaSchool of Electronic Systems and Automation, Digital University Kerala, Trivandrum, Kerala, IndiaSystem level simulation of neuro-memristive circuits under variability are complex and follow a black-box neural network approach. In realistic hardware, they are often difficult to cross-check for accuracy and reproducible results. The accurate memristor model prediction becomes critical to decipher the overall circuit function in a wide range of nonideal and practical conditions. In most neuro-memristive systems, crossbar configuration is essential for implementing multiply and accumulate calculations, that form the primary unit for neural network implementations. Predicting the specific memristor model that best fits the crossbar simulations to make it explainable is an open challenge that is solved in this article. As the size of the crossbar increases the cross-validation becomes even more challenging. This article proposes predicting the memristor device under test by automatically evaluating the <italic>I–V</italic> behavior using random forest and extreme gradient boosting algorithms. Starting with a single memristor model, the prediction approach is extended to memristor crossbar-based circuits explainable. The performance of both algorithms is analyzed based on precision, recall, f1-score, and support. The accuracy, macro average, and weighted average of both algorithms at different operational frequencies are explored.https://ieeexplore.ieee.org/document/10631696/Extreme gradient boost (XGBoost) predictormemristor modelsmemristor crossbarpinched hysteresisrandom forest predictor |
| spellingShingle | Sruthi Pallathuvalappil Rahul Kottappuzhackal Alex James Explainable Model Prediction of Memristor IEEE Open Journal of the Industrial Electronics Society Extreme gradient boost (XGBoost) predictor memristor models memristor crossbar pinched hysteresis random forest predictor |
| title | Explainable Model Prediction of Memristor |
| title_full | Explainable Model Prediction of Memristor |
| title_fullStr | Explainable Model Prediction of Memristor |
| title_full_unstemmed | Explainable Model Prediction of Memristor |
| title_short | Explainable Model Prediction of Memristor |
| title_sort | explainable model prediction of memristor |
| topic | Extreme gradient boost (XGBoost) predictor memristor models memristor crossbar pinched hysteresis random forest predictor |
| url | https://ieeexplore.ieee.org/document/10631696/ |
| work_keys_str_mv | AT sruthipallathuvalappil explainablemodelpredictionofmemristor AT rahulkottappuzhackal explainablemodelpredictionofmemristor AT alexjames explainablemodelpredictionofmemristor |