RRAM resistive switching behavior evaluation and prediction, based on fabrication conditions. Applied Machine learning\Deep learning models to predict SET voltage distribution in Honey-based RRAM devices. Simulating the basic operations of RRAM crossbars in image classification tasks, investigating the robustness of in situ vs. ex situ training.
Applied both machine learning and deep learning models to predict SET voltage distribution in Honey-based RRAM devices, assessing the likelihood of observing specific voltage values based on fabrication conditions. Developed an application that simulates the basic operations of RRAM devices in image classification tasks; used ex situ offline training methods and mapped neural network weights onto RRAM crossbars to evaluate their tolerance to weight noise and deviations. Investigated the robustness of in situ vs. ex situ training methods in the context of weight tolerance.
- Title: "A Machine Learning Approach to Support Neuromorphic Device Design and Microfabrication"
- Authors: A. Y. Vicenciodelmoral, M. M. Hasan Tanim, F. Zhao, X. Zhao
- Publication: 2023 International Conference on Machine Learning and Applications (ICMLA)
- Date: 2023
- DOI: 10.1109/ICMLA58977.2023.00246
- Pages: 1627-1634
- Title: "An end-to-end learning framework for supporting green neuromorphic computing: From RRAM design and microfabrication to applications"
- Authors: A. Y. Vicenciodelmoral
- Publication: Dissertations & Theses @ Washington State University WCLP; ProQuest Dissertations & Theses A&I
- Date: 2023
- URL: Access Document
- Order No.: 30631228