Ultralow power dual-gated subthreshold oxide neuristors : an enabler for higher order neuronal temporal correlations
Inspired by neural computing, the pursuit of ultralow power neuromorphic architectures with highly distributed memory and parallel processing capability has recently gained more traction. However, emulation of biological signal processing via artificial neuromorphic architectures does not exploit th...
| Main Authors: | , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/138428 |
| _version_ | 1826124095013519360 |
|---|---|
| author | John, Rohit Abharam Tiwari, Nidhi Chen, Yaoyi Ankit Tiwari, Naveen Kulkarni, Mohit Nirmal, Amoolya Nguyen, Anh Chien Basu, Arindam Mathews, Nripan |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering John, Rohit Abharam Tiwari, Nidhi Chen, Yaoyi Ankit Tiwari, Naveen Kulkarni, Mohit Nirmal, Amoolya Nguyen, Anh Chien Basu, Arindam Mathews, Nripan |
| author_sort | John, Rohit Abharam |
| collection | NTU |
| description | Inspired by neural computing, the pursuit of ultralow power neuromorphic architectures with highly distributed memory and parallel processing capability has recently gained more traction. However, emulation of biological signal processing via artificial neuromorphic architectures does not exploit the immense interplay between local activities and global neuromodulations observed in biological neural networks and hence are unable to mimic complex biologically plausible adaptive functions like heterosynaptic plasticity and homeostasis. Here, we demonstrate emulation of complex neuronal behaviors like heterosynaptic plasticity, homeostasis, association, correlation, and coincidence in a single neuristor via a dual-gated architecture. This multiple gating approach allows one gate to capture the effect of local activity correlations and the second gate to represent global neuromodulations, allowing additional modulations which augment their plasticity, enabling higher order temporal correlations at a unitary level. Moreover, the dual-gate operation extends the available dynamic range of synaptic conductance while maintaining symmetry in the weight-update operation, expanding the number of accessible memory states. Finally, operating neuristors in the subthreshold regime enable synaptic weight changes with high gain while maintaining ultralow power consumption of the order of femto-Joules. |
| first_indexed | 2024-10-01T06:15:03Z |
| format | Journal Article |
| id | ntu-10356/138428 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:15:03Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1384282023-07-14T16:00:21Z Ultralow power dual-gated subthreshold oxide neuristors : an enabler for higher order neuronal temporal correlations John, Rohit Abharam Tiwari, Nidhi Chen, Yaoyi Ankit Tiwari, Naveen Kulkarni, Mohit Nirmal, Amoolya Nguyen, Anh Chien Basu, Arindam Mathews, Nripan School of Electrical and Electronic Engineering School of Materials Science & Engineering Energy Research Institute @ NTU (ERI@N) Engineering::Materials Synaptic Transistors Neuromorphic Computing Inspired by neural computing, the pursuit of ultralow power neuromorphic architectures with highly distributed memory and parallel processing capability has recently gained more traction. However, emulation of biological signal processing via artificial neuromorphic architectures does not exploit the immense interplay between local activities and global neuromodulations observed in biological neural networks and hence are unable to mimic complex biologically plausible adaptive functions like heterosynaptic plasticity and homeostasis. Here, we demonstrate emulation of complex neuronal behaviors like heterosynaptic plasticity, homeostasis, association, correlation, and coincidence in a single neuristor via a dual-gated architecture. This multiple gating approach allows one gate to capture the effect of local activity correlations and the second gate to represent global neuromodulations, allowing additional modulations which augment their plasticity, enabling higher order temporal correlations at a unitary level. Moreover, the dual-gate operation extends the available dynamic range of synaptic conductance while maintaining symmetry in the weight-update operation, expanding the number of accessible memory states. Finally, operating neuristors in the subthreshold regime enable synaptic weight changes with high gain while maintaining ultralow power consumption of the order of femto-Joules. MOE (Min. of Education, S’pore) Accepted version 2020-05-06T02:42:34Z 2020-05-06T02:42:34Z 2018 Journal Article John, R. A., Tiwari, N., Chen, Y., Ankit, Tiwari, N., Kulkarni, M., . . . Mathews, N. (2018). Ultralow power dual-gated subthreshold oxide neuristors : an enabler for higher order neuronal temporal correlations. ACS nano, 12(11), 11263-11273. doi:10.1021/acsnano.8b05903 1936-0851 https://hdl.handle.net/10356/138428 10.1021/acsnano.8b05903 11 12 11263 11273 en ACS Nano https://doi.org/10.21979/N9/9VPOSU This document is the Accepted Manuscript version of a Published Work that appeared in final form in ACS Nano, copyright © American Chemical Society after peer review and technical editing by the publisher. To access the final edited and published work see https://doi.org/10.1021/acsnano.8b05903 application/pdf |
| spellingShingle | Engineering::Materials Synaptic Transistors Neuromorphic Computing John, Rohit Abharam Tiwari, Nidhi Chen, Yaoyi Ankit Tiwari, Naveen Kulkarni, Mohit Nirmal, Amoolya Nguyen, Anh Chien Basu, Arindam Mathews, Nripan Ultralow power dual-gated subthreshold oxide neuristors : an enabler for higher order neuronal temporal correlations |
| title | Ultralow power dual-gated subthreshold oxide neuristors : an enabler for higher order neuronal temporal correlations |
| title_full | Ultralow power dual-gated subthreshold oxide neuristors : an enabler for higher order neuronal temporal correlations |
| title_fullStr | Ultralow power dual-gated subthreshold oxide neuristors : an enabler for higher order neuronal temporal correlations |
| title_full_unstemmed | Ultralow power dual-gated subthreshold oxide neuristors : an enabler for higher order neuronal temporal correlations |
| title_short | Ultralow power dual-gated subthreshold oxide neuristors : an enabler for higher order neuronal temporal correlations |
| title_sort | ultralow power dual gated subthreshold oxide neuristors an enabler for higher order neuronal temporal correlations |
| topic | Engineering::Materials Synaptic Transistors Neuromorphic Computing |
| url | https://hdl.handle.net/10356/138428 |
| work_keys_str_mv | AT johnrohitabharam ultralowpowerdualgatedsubthresholdoxideneuristorsanenablerforhigherorderneuronaltemporalcorrelations AT tiwarinidhi ultralowpowerdualgatedsubthresholdoxideneuristorsanenablerforhigherorderneuronaltemporalcorrelations AT chenyaoyi ultralowpowerdualgatedsubthresholdoxideneuristorsanenablerforhigherorderneuronaltemporalcorrelations AT ankit ultralowpowerdualgatedsubthresholdoxideneuristorsanenablerforhigherorderneuronaltemporalcorrelations AT tiwarinaveen ultralowpowerdualgatedsubthresholdoxideneuristorsanenablerforhigherorderneuronaltemporalcorrelations AT kulkarnimohit ultralowpowerdualgatedsubthresholdoxideneuristorsanenablerforhigherorderneuronaltemporalcorrelations AT nirmalamoolya ultralowpowerdualgatedsubthresholdoxideneuristorsanenablerforhigherorderneuronaltemporalcorrelations AT nguyenanhchien ultralowpowerdualgatedsubthresholdoxideneuristorsanenablerforhigherorderneuronaltemporalcorrelations AT basuarindam ultralowpowerdualgatedsubthresholdoxideneuristorsanenablerforhigherorderneuronaltemporalcorrelations AT mathewsnripan ultralowpowerdualgatedsubthresholdoxideneuristorsanenablerforhigherorderneuronaltemporalcorrelations |