Phase Coupling and Control of Oxide-Based Oscillators for Neuromorphic Computing
Neuromorphic computing using neural network hardware has attracted significant interest as it promises improved performance at low power for data-intensive error-resilient graphical signal processing. Oscillatory neural networks (ONNs) use either frequency or phase as state variables to implement fr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2015-01-01
|
| Series: | IEEE Journal on Exploratory Solid-State Computational Devices and Circuits |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/7140766/ |
| _version_ | 1818619512995446784 |
|---|---|
| author | Abhishek A. Sharma James A. Bain Jeffrey A. Weldon |
| author_facet | Abhishek A. Sharma James A. Bain Jeffrey A. Weldon |
| author_sort | Abhishek A. Sharma |
| collection | DOAJ |
| description | Neuromorphic computing using neural network hardware has attracted significant interest as it promises improved performance at low power for data-intensive error-resilient graphical signal processing. Oscillatory neural networks (ONNs) use either frequency or phase as state variables to implement frequency-shift keying (FSK)- and phase-shift keying (PSK)-based neural networks, respectively. To make these ONNs power and area efficient, back-end-of-the-line compatible, and capable of processing multilevel information, we explore an emerging class of oscillators that show fine-grain frequency-tuning and phase-coupling. We examine TaOx- and TiOx-based oscillators (resistive random access memory-type) as elements of a neuromorphic compute block and experimentally demonstrate: 1) frequency control over four decades using a ballast MOSFET; 2) variable phase coupling between oscillators; and 3) variable phase programming between oscillators coupled with a MOSFET. Such fine-grain control over both frequency and relative phase serve as the desirable characteristics of oscillators required for multilevel information processing in star-type directly coupled FSK- and PSK-based neuromorphic systems that find applications in gray-scale image processing and other graphical compute paradigms. These attributes combined with the small size (<;1 μm<sup>2</sup>) and simplicity, make these devices attractive candidates for realizing large-scale neuromorphic systems at reasonable size and power. |
| first_indexed | 2024-12-16T17:38:40Z |
| format | Article |
| id | doaj.art-f18f9140be6d4182bfa5455de274724f |
| institution | Directory Open Access Journal |
| issn | 2329-9231 |
| language | English |
| last_indexed | 2024-12-16T17:38:40Z |
| publishDate | 2015-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal on Exploratory Solid-State Computational Devices and Circuits |
| spelling | doaj.art-f18f9140be6d4182bfa5455de274724f2022-12-21T22:22:40ZengIEEEIEEE Journal on Exploratory Solid-State Computational Devices and Circuits2329-92312015-01-011586610.1109/JXCDC.2015.24484177140766Phase Coupling and Control of Oxide-Based Oscillators for Neuromorphic ComputingAbhishek A. Sharma0James A. Bain1Jeffrey A. Weldon2Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USADepartment of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USADepartment of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USANeuromorphic computing using neural network hardware has attracted significant interest as it promises improved performance at low power for data-intensive error-resilient graphical signal processing. Oscillatory neural networks (ONNs) use either frequency or phase as state variables to implement frequency-shift keying (FSK)- and phase-shift keying (PSK)-based neural networks, respectively. To make these ONNs power and area efficient, back-end-of-the-line compatible, and capable of processing multilevel information, we explore an emerging class of oscillators that show fine-grain frequency-tuning and phase-coupling. We examine TaOx- and TiOx-based oscillators (resistive random access memory-type) as elements of a neuromorphic compute block and experimentally demonstrate: 1) frequency control over four decades using a ballast MOSFET; 2) variable phase coupling between oscillators; and 3) variable phase programming between oscillators coupled with a MOSFET. Such fine-grain control over both frequency and relative phase serve as the desirable characteristics of oscillators required for multilevel information processing in star-type directly coupled FSK- and PSK-based neuromorphic systems that find applications in gray-scale image processing and other graphical compute paradigms. These attributes combined with the small size (<;1 μm<sup>2</sup>) and simplicity, make these devices attractive candidates for realizing large-scale neuromorphic systems at reasonable size and power.https://ieeexplore.ieee.org/document/7140766/Oxide OscillatorsRelaxation OscillatorsNeuromorphic ComputingCoupled OscillatorsOscillatory Neural NetworksTaOx |
| spellingShingle | Abhishek A. Sharma James A. Bain Jeffrey A. Weldon Phase Coupling and Control of Oxide-Based Oscillators for Neuromorphic Computing IEEE Journal on Exploratory Solid-State Computational Devices and Circuits Oxide Oscillators Relaxation Oscillators Neuromorphic Computing Coupled Oscillators Oscillatory Neural Networks TaOx |
| title | Phase Coupling and Control of Oxide-Based Oscillators for Neuromorphic Computing |
| title_full | Phase Coupling and Control of Oxide-Based Oscillators for Neuromorphic Computing |
| title_fullStr | Phase Coupling and Control of Oxide-Based Oscillators for Neuromorphic Computing |
| title_full_unstemmed | Phase Coupling and Control of Oxide-Based Oscillators for Neuromorphic Computing |
| title_short | Phase Coupling and Control of Oxide-Based Oscillators for Neuromorphic Computing |
| title_sort | phase coupling and control of oxide based oscillators for neuromorphic computing |
| topic | Oxide Oscillators Relaxation Oscillators Neuromorphic Computing Coupled Oscillators Oscillatory Neural Networks TaOx |
| url | https://ieeexplore.ieee.org/document/7140766/ |
| work_keys_str_mv | AT abhishekasharma phasecouplingandcontrolofoxidebasedoscillatorsforneuromorphiccomputing AT jamesabain phasecouplingandcontrolofoxidebasedoscillatorsforneuromorphiccomputing AT jeffreyaweldon phasecouplingandcontrolofoxidebasedoscillatorsforneuromorphiccomputing |