Forming-less compliance-free multistate memristors as synaptic connections for brain-inspired computing
Hardware realization of artificial neural networks (ANNs) requires analogue weights to be encoded into the device conductances via blind update and access operations, leveraging Kirchhoff’s circuit laws. However, most memristive solutions lag behind in this aspect due to numerous device nonidealitie...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/140531 |
| _version_ | 1826124996150296576 |
|---|---|
| author | Ng, Sien John, Rohit Abraham Yang, Jing-ting Mathews, Nripan |
| author2 | School of Materials Science and Engineering |
| author_facet | School of Materials Science and Engineering Ng, Sien John, Rohit Abraham Yang, Jing-ting Mathews, Nripan |
| author_sort | Ng, Sien |
| collection | NTU |
| description | Hardware realization of artificial neural networks (ANNs) requires analogue weights to be encoded into the device conductances via blind update and access operations, leveraging Kirchhoff’s circuit laws. However, most memristive solutions lag behind in this aspect due to numerous device nonidealities, like limited number of addressable states, need for a stringent compliance current control, and an electroforming process. By modulating the oxygen vacancy profile of tin oxide switching elements, here we design and evaluate multistate memristors as synaptic connections for brain-inspired computing. Harnessing the advantages of a forming-less compliance-free operation, our devices display gradual switching transitions across multiple conductance states, sufficing the switching requirements of synaptic connections in an ANN. The soft boundary conditions are analyzed systematically, and spike-based plasticity rules, state-dependent spike-timing-dependent-plasticity (STDP) modulations, ternary digital logic, and analogue updatability schemes are proposed and demonstrated comprehensively to establish the analogue programming window of our memristors. |
| first_indexed | 2024-10-01T06:29:30Z |
| format | Journal Article |
| id | ntu-10356/140531 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:29:30Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1405312023-07-14T15:58:13Z Forming-less compliance-free multistate memristors as synaptic connections for brain-inspired computing Ng, Sien John, Rohit Abraham Yang, Jing-ting Mathews, Nripan School of Materials Science and Engineering Energy Research Institute @ NTU (ERI@N) Engineering::Materials Forming-less Compliance-free Hardware realization of artificial neural networks (ANNs) requires analogue weights to be encoded into the device conductances via blind update and access operations, leveraging Kirchhoff’s circuit laws. However, most memristive solutions lag behind in this aspect due to numerous device nonidealities, like limited number of addressable states, need for a stringent compliance current control, and an electroforming process. By modulating the oxygen vacancy profile of tin oxide switching elements, here we design and evaluate multistate memristors as synaptic connections for brain-inspired computing. Harnessing the advantages of a forming-less compliance-free operation, our devices display gradual switching transitions across multiple conductance states, sufficing the switching requirements of synaptic connections in an ANN. The soft boundary conditions are analyzed systematically, and spike-based plasticity rules, state-dependent spike-timing-dependent-plasticity (STDP) modulations, ternary digital logic, and analogue updatability schemes are proposed and demonstrated comprehensively to establish the analogue programming window of our memristors. MOE (Min. of Education, S’pore) Accepted version 2020-05-30T07:43:05Z 2020-05-30T07:43:05Z 2020 Journal Article Ng, S., John, R. A., Yang, J.-t., & Mathews, N. (2020). Forming-less compliance-free multistate memristors as synaptic connections for brain-inspired computing. ACS Applied Electronic Materials, 2(3), 817-826. doi:10.1021/acsaelm.0c00002 2637-6113 https://hdl.handle.net/10356/140531 10.1021/acsaelm.0c00002 3 2 817 826 en MOE2016-T2-1100 MOE2018-T2-2-083 ACS Applied Electronic Materials https://doi.org/10.21979/N9/YWTJBM This document is the Accepted Manuscript version of a Published Work that appeared in final form in ACS Applied Electronic Materials, 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/acsaelm.0c00002 application/pdf |
| spellingShingle | Engineering::Materials Forming-less Compliance-free Ng, Sien John, Rohit Abraham Yang, Jing-ting Mathews, Nripan Forming-less compliance-free multistate memristors as synaptic connections for brain-inspired computing |
| title | Forming-less compliance-free multistate memristors as synaptic connections for brain-inspired computing |
| title_full | Forming-less compliance-free multistate memristors as synaptic connections for brain-inspired computing |
| title_fullStr | Forming-less compliance-free multistate memristors as synaptic connections for brain-inspired computing |
| title_full_unstemmed | Forming-less compliance-free multistate memristors as synaptic connections for brain-inspired computing |
| title_short | Forming-less compliance-free multistate memristors as synaptic connections for brain-inspired computing |
| title_sort | forming less compliance free multistate memristors as synaptic connections for brain inspired computing |
| topic | Engineering::Materials Forming-less Compliance-free |
| url | https://hdl.handle.net/10356/140531 |
| work_keys_str_mv | AT ngsien forminglesscompliancefreemultistatememristorsassynapticconnectionsforbraininspiredcomputing AT johnrohitabraham forminglesscompliancefreemultistatememristorsassynapticconnectionsforbraininspiredcomputing AT yangjingting forminglesscompliancefreemultistatememristorsassynapticconnectionsforbraininspiredcomputing AT mathewsnripan forminglesscompliancefreemultistatememristorsassynapticconnectionsforbraininspiredcomputing |