File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1126/sciadv.abg1455
- Scopus: eid_2-s2.0-85105961268
- PMID: 33990331
- WOS: WOS:000652258100030
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: In-sensor reservoir computing for language learning via two-dimensional memristors
Title | In-sensor reservoir computing for language learning via two-dimensional memristors |
---|---|
Authors | |
Issue Date | 2021 |
Publisher | American Association for the Advancement of Science: Science Advances. The Journal's web site is located at http://www.scienceadvances.org/ |
Citation | Science Advances, 2021, v. 7 n. 20, p. article no. eabg1455 How to Cite? |
Abstract | The dynamic processing of optoelectronic signals carrying temporal and sequential information is critical to various machine learning applications including language processing and computer vision. Despite extensive efforts to emulate the visual cortex of human brain, large energy/time overhead and extra hardware costs are incurred by the physically separated sensing, memory, and processing units. The challenge is further intensified by the tedious training of conventional recurrent neural networks for edge deployment. Here, we report in-sensor reservoir computing for language learning. High dimensionality, nonlinearity, and fading memory for the in-sensor reservoir were achieved via two-dimensional memristors based on tin sulfide (SnS), uniquely having dual-type defect states associated with Sn and S vacancies. Our in-sensor reservoir computing demonstrates an accuracy of 91% to classify short sentences of language, thus shedding light on a low training cost and the real-time solution for processing temporal and sequential signals for machine learning applications at the edge. |
Persistent Identifier | http://hdl.handle.net/10722/305805 |
ISSN | 2023 Impact Factor: 11.7 2023 SCImago Journal Rankings: 4.483 |
PubMed Central ID | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Sun, L | - |
dc.contributor.author | Wang, Z | - |
dc.contributor.author | Jiang, J | - |
dc.contributor.author | Kim, Y | - |
dc.contributor.author | Joo, B | - |
dc.contributor.author | Zheng, S | - |
dc.contributor.author | Lee, S | - |
dc.contributor.author | Yu, W | - |
dc.contributor.author | Kong, B | - |
dc.contributor.author | Yang, H | - |
dc.date.accessioned | 2021-10-20T10:14:34Z | - |
dc.date.available | 2021-10-20T10:14:34Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Science Advances, 2021, v. 7 n. 20, p. article no. eabg1455 | - |
dc.identifier.issn | 2375-2548 | - |
dc.identifier.uri | http://hdl.handle.net/10722/305805 | - |
dc.description.abstract | The dynamic processing of optoelectronic signals carrying temporal and sequential information is critical to various machine learning applications including language processing and computer vision. Despite extensive efforts to emulate the visual cortex of human brain, large energy/time overhead and extra hardware costs are incurred by the physically separated sensing, memory, and processing units. The challenge is further intensified by the tedious training of conventional recurrent neural networks for edge deployment. Here, we report in-sensor reservoir computing for language learning. High dimensionality, nonlinearity, and fading memory for the in-sensor reservoir were achieved via two-dimensional memristors based on tin sulfide (SnS), uniquely having dual-type defect states associated with Sn and S vacancies. Our in-sensor reservoir computing demonstrates an accuracy of 91% to classify short sentences of language, thus shedding light on a low training cost and the real-time solution for processing temporal and sequential signals for machine learning applications at the edge. | - |
dc.language | eng | - |
dc.publisher | American Association for the Advancement of Science: Science Advances. The Journal's web site is located at http://www.scienceadvances.org/ | - |
dc.relation.ispartof | Science Advances | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.title | In-sensor reservoir computing for language learning via two-dimensional memristors | - |
dc.type | Article | - |
dc.identifier.email | Wang, Z: zrwang@eee.hku.hk | - |
dc.identifier.authority | Wang, Z=rp02714 | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.1126/sciadv.abg1455 | - |
dc.identifier.pmid | 33990331 | - |
dc.identifier.pmcid | PMC8121431 | - |
dc.identifier.scopus | eid_2-s2.0-85105961268 | - |
dc.identifier.hkuros | 327768 | - |
dc.identifier.volume | 7 | - |
dc.identifier.issue | 20 | - |
dc.identifier.spage | article no. eabg1455 | - |
dc.identifier.epage | article no. eabg1455 | - |
dc.identifier.isi | WOS:000652258100030 | - |
dc.publisher.place | United States | - |