PyMem: A Graphical User Interface Tool for Neuromemristive Hardware–Software Co-Design
The hardware implementation of neuromorphic system requires energy and area-efficient hardware. Memristor-based hardware architectures is a promising approach that naturally mimics the switching behavior of the neuron models. However, to build complex neural systems, it is a tedious process to selec...
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/10423246/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526319947448320 |
|---|---|
| author | Aswani Radhakrishnan Jushnah Palliyalil Sreeja Babu Anuar Dorzhigulov Alex James |
| author_facet | Aswani Radhakrishnan Jushnah Palliyalil Sreeja Babu Anuar Dorzhigulov Alex James |
| author_sort | Aswani Radhakrishnan |
| collection | DOAJ |
| description | The hardware implementation of neuromorphic system requires energy and area-efficient hardware. Memristor-based hardware architectures is a promising approach that naturally mimics the switching behavior of the neuron models. However, to build complex neural systems, it is a tedious process to select the right memristor models and architectures that are suitable to be used in a range of realistic conditions. To simplify the design and development of neuromemristive architectures, we present a web-based graphical user interface (GUI) called “PyMem” that uses Keras Python to implement multiple memristor models on multiple neural architectures that can be used to analyze their working under a wide range of hardware variability. Without the need for programming, the GUI provides options for adding variability to the memristors and observing the neural network behavior under realistic conditions. The tool has options to characterize the ideal (software) and nonideal (hardware) for performance analysis including accuracy, precision, recall, and relative current error values. |
| format | Article |
| id | doaj-art-042061ae82024c3ca3d1add20fec039c |
| 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-042061ae82024c3ca3d1add20fec039c2025-01-17T00:00:57ZengIEEEIEEE Open Journal of the Industrial Electronics Society2644-12842024-01-015819010.1109/OJIES.2024.336309310423246PyMem: A Graphical User Interface Tool for Neuromemristive Hardware–Software Co-DesignAswani Radhakrishnan0https://orcid.org/0000-0002-1086-1870Jushnah Palliyalil1https://orcid.org/0009-0008-2202-5950Sreeja Babu2https://orcid.org/0009-0007-3660-9765Anuar Dorzhigulov3https://orcid.org/0009-0005-6475-5490Alex James4https://orcid.org/0000-0001-5655-1213Digital University Kerala, Trivandrum, IndiaDigital University Kerala, Trivandrum, IndiaDigital University Kerala, Trivandrum, IndiaUniversity of Delaware, Newark, DE, USADigital University Kerala, Trivandrum, IndiaThe hardware implementation of neuromorphic system requires energy and area-efficient hardware. Memristor-based hardware architectures is a promising approach that naturally mimics the switching behavior of the neuron models. However, to build complex neural systems, it is a tedious process to select the right memristor models and architectures that are suitable to be used in a range of realistic conditions. To simplify the design and development of neuromemristive architectures, we present a web-based graphical user interface (GUI) called “PyMem” that uses Keras Python to implement multiple memristor models on multiple neural architectures that can be used to analyze their working under a wide range of hardware variability. Without the need for programming, the GUI provides options for adding variability to the memristors and observing the neural network behavior under realistic conditions. The tool has options to characterize the ideal (software) and nonideal (hardware) for performance analysis including accuracy, precision, recall, and relative current error values.https://ieeexplore.ieee.org/document/10423246/Memristorneural networkoptimizationvariability |
| spellingShingle | Aswani Radhakrishnan Jushnah Palliyalil Sreeja Babu Anuar Dorzhigulov Alex James PyMem: A Graphical User Interface Tool for Neuromemristive Hardware–Software Co-Design IEEE Open Journal of the Industrial Electronics Society Memristor neural network optimization variability |
| title | PyMem: A Graphical User Interface Tool for Neuromemristive Hardware–Software Co-Design |
| title_full | PyMem: A Graphical User Interface Tool for Neuromemristive Hardware–Software Co-Design |
| title_fullStr | PyMem: A Graphical User Interface Tool for Neuromemristive Hardware–Software Co-Design |
| title_full_unstemmed | PyMem: A Graphical User Interface Tool for Neuromemristive Hardware–Software Co-Design |
| title_short | PyMem: A Graphical User Interface Tool for Neuromemristive Hardware–Software Co-Design |
| title_sort | pymem a graphical user interface tool for neuromemristive hardware x2013 software co design |
| topic | Memristor neural network optimization variability |
| url | https://ieeexplore.ieee.org/document/10423246/ |
| work_keys_str_mv | AT aswaniradhakrishnan pymemagraphicaluserinterfacetoolforneuromemristivehardwarex2013softwarecodesign AT jushnahpalliyalil pymemagraphicaluserinterfacetoolforneuromemristivehardwarex2013softwarecodesign AT sreejababu pymemagraphicaluserinterfacetoolforneuromemristivehardwarex2013softwarecodesign AT anuardorzhigulov pymemagraphicaluserinterfacetoolforneuromemristivehardwarex2013softwarecodesign AT alexjames pymemagraphicaluserinterfacetoolforneuromemristivehardwarex2013softwarecodesign |