Exploring Spike Encoder Designs for Near-Sensor Edge Computing
Robust sensing and detection require energy- and cost-efficient hardware and software capable of operating reliably in dynamic environments with wide variations in operating conditions. Spiking Neural Networks (SNNs), widely recognized as biologically inspired computing models, offer significant pot...
Uloženo v:
| Vydáno v: | 2025 Neuro Inspired Computational Elements (NICE) s. 1 - 9 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
25.03.2025
|
| Témata: | |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Robust sensing and detection require energy- and cost-efficient hardware and software capable of operating reliably in dynamic environments with wide variations in operating conditions. Spiking Neural Networks (SNNs), widely recognized as biologically inspired computing models, offer significant potential for near-sensor signal processing due to their energy efficiency and adaptability. A critical step toward broader adoption of this novel computing paradigm is the development of efficient frontend designs capable of encoding multichannel time-series data from sensors into sparse spike trains. This work introduces two spike-encoder architectures: a population coding-based encoder and a reservoir computing- based encoder. These architectures convert multivariate time series into multichannel spike sequences, performing sparse coding that effectively projects the input temporal sequences into a high-dimensional binary feature space in both spatial and temporal domains. When combined with an SNN-based backend classifier, the encoded spike sequences enable effective classification. Furthermore, our proposed reservoir encoder achieves lower implementation complexity compared to conventional reservoir models while maintaining effective sparse coding capabilities. Finally, we demonstrate that the in- hardware online learning capability of SNN models can alleviate stringent requirements on encoder performance and precision to allow cost reduction and design simplification. |
|---|---|
| AbstractList | Robust sensing and detection require energy- and cost-efficient hardware and software capable of operating reliably in dynamic environments with wide variations in operating conditions. Spiking Neural Networks (SNNs), widely recognized as biologically inspired computing models, offer significant potential for near-sensor signal processing due to their energy efficiency and adaptability. A critical step toward broader adoption of this novel computing paradigm is the development of efficient frontend designs capable of encoding multichannel time-series data from sensors into sparse spike trains. This work introduces two spike-encoder architectures: a population coding-based encoder and a reservoir computing- based encoder. These architectures convert multivariate time series into multichannel spike sequences, performing sparse coding that effectively projects the input temporal sequences into a high-dimensional binary feature space in both spatial and temporal domains. When combined with an SNN-based backend classifier, the encoded spike sequences enable effective classification. Furthermore, our proposed reservoir encoder achieves lower implementation complexity compared to conventional reservoir models while maintaining effective sparse coding capabilities. Finally, we demonstrate that the in- hardware online learning capability of SNN models can alleviate stringent requirements on encoder performance and precision to allow cost reduction and design simplification. |
| Author | Jin, Jingang Zhang, Zhenhang Qiu, Qinru |
| Author_xml | – sequence: 1 givenname: Jingang surname: Jin fullname: Jin, Jingang email: jjin24@syr.edu organization: Syracuse University,Department of Electrical Engineering and Computer Science – sequence: 2 givenname: Zhenhang surname: Zhang fullname: Zhang, Zhenhang email: zzhan281@syr.edu organization: Syracuse University,Department of Electrical Engineering and Computer Science – sequence: 3 givenname: Qinru surname: Qiu fullname: Qiu, Qinru email: qinru.qiu@gmail.com organization: Syracuse University,Department of Electrical Engineering and Computer Science |
| BookMark | eNo1j89KAzEYxCPYg9a-QcG8wNYkX_5eBFnXWij10N5L2v2yBNtkyVbQt3dFncsMP5iBuSXXKSck5J6zBefMPWxWdaMVKLYQTKgfppVg-orMnHEWgCsGTMgb8th89qdcYuroto_vSJt0zC0W-oxD7NJAQy50g75UW0zDmJu2Q1rnc_9xGUt3ZBL8acDZn0_J7qXZ1a_V-m25qp_WVeTGXioPzIjgeAgSrPVokBmpJBwx2FFCo9UHKTBoPDg0Ep3QwGWQQrRecpiS-e9sRMR9X-LZl6_9_yv4BvqdRfM |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/NICE65350.2025.11065206 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 9798331503024 |
| EndPage | 9 |
| ExternalDocumentID | 11065206 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IL CBEJK RIE RIL |
| ID | FETCH-LOGICAL-i178t-a3072f91ff4388ae7e074543cef888826e86b42ef6eb9e74e926314f422da413 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001553129800012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Jul 16 07:54:06 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i178t-a3072f91ff4388ae7e074543cef888826e86b42ef6eb9e74e926314f422da413 |
| PageCount | 9 |
| ParticipantIDs | ieee_primary_11065206 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-March-25 |
| PublicationDateYYYYMMDD | 2025-03-25 |
| PublicationDate_xml | – month: 03 year: 2025 text: 2025-March-25 day: 25 |
| PublicationDecade | 2020 |
| PublicationTitle | 2025 Neuro Inspired Computational Elements (NICE) |
| PublicationTitleAbbrev | NICE |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| Score | 1.9033731 |
| Snippet | Robust sensing and detection require energy- and cost-efficient hardware and software capable of operating reliably in dynamic environments with wide... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Adaptation models Complexity theory Computational modeling Computer architecture Costs Edge computing Encoding Hardware in-Hardware Learning Reservoirs SNN Spike encoder Transforms |
| Title | Exploring Spike Encoder Designs for Near-Sensor Edge Computing |
| URI | https://ieeexplore.ieee.org/document/11065206 |
| WOSCitedRecordID | wos001553129800012&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09a8MwEBVt6NCpLU3pNxq6KrH1aS1dUod2MYFkyBZs61RCwQn5-v09yUlKhw5dhBA2QrLNuye_d0fIS-qsqYSTzCI6M-kdZ7auLTaZ5KAdhiBJLDZhiiKbTu1ob1aPXhgAiOIz6IVu_JfvFvU2HJX1Eaq04iHB9qkxujVr7TVbaWL7xccg10qoBGkfV73D1b_qpkTYGF78c8JL0v0x4NHREVquyAk01-T1qJej4-X8C2jeBEP6ir5FFcaaYvxJC3xz2Ri5KfZz9wm0LduAN3XJZJhPBu9sX_6AzVOTbViJnx_3NvVeiiwrwQDCvZKiBo-0FWkBZLrCDfUaKgtGguVapNJLzl2J2HRDOs2igVtCQ5BTJcJCYD-qDFFAqkOmLSW0s3V5R7ph7bNlm-Bidlj2_R_jD-Q87HCQYnH1SDqb1RaeyFm928zXq-f4WL4BcxKM7g |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA4yBT2pOPG3OXjN1uZXm4uX2bHhLIPtsNtomxcZQjf2w7_fl2xTPHjwEkJoCUlbvvel3_ceIU-xNUkprGQG0ZlJZzkzVWWwSSUHbTEEiUKxiSTP08nEDHdm9eCFAYAgPoOW74Z_-XZebfxRWRuhSivuE2wfKil5tLVr7VRbcWTaeb-TaSVUhMSPq9b--l-VUwJwdE__OeUZaf5Y8OjwG1zOyQHUF-T5WzFHR4vZB9Cs9pb0JX0JOowVxQiU5vjushGyU-xn9h3otnAD3tQk42427vTYrgACm8VJumYFfoDcmdg5KdK0gAQQ8JUUFTgkrkgMINUlbqnTUBpIJBiuRSyd5NwWiE6XpFHPa7gi1Ic5ZSQMeP6jCh8HxNrn2lJCW1MV16Tp1z5dbFNcTPfLvvlj_JEc98Zvg-mgn7_ekhO_216YxdUdaayXG7gnR9XnerZaPoRH9AX8LpA1 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+Neuro+Inspired+Computational+Elements+%28NICE%29&rft.atitle=Exploring+Spike+Encoder+Designs+for+Near-Sensor+Edge+Computing&rft.au=Jin%2C+Jingang&rft.au=Zhang%2C+Zhenhang&rft.au=Qiu%2C+Qinru&rft.date=2025-03-25&rft.pub=IEEE&rft.spage=1&rft.epage=9&rft_id=info:doi/10.1109%2FNICE65350.2025.11065206&rft.externalDocID=11065206 |