The Heidelberg spiking data sets for the systematic evaluation of spiking neural networks
Spiking neural networks are the basis of versatile and power-efficient information processing in the brain. Although we currently lack a detailed understanding of how these networks compute, recently developed optimization techniques allow us to instantiate increasingly complex functional spiking ne...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
July 2022
|
| In: |
IEEE transactions on neural networks and learning systems
Year: 2022, Jahrgang: 33, Heft: 7, Pages: 2744-2757 |
| ISSN: | 2162-2388 |
| DOI: | 10.1109/TNNLS.2020.3044364 |
| Online-Zugang: | Resolving-System, kostenfrei, Volltext: https://doi.org/10.1109/TNNLS.2020.3044364 Verlag, kostenfrei, Volltext: https://ieeexplore.ieee.org/document/9311226 
|
| Verfasserangaben: | Benjamin Cramer, Yannik Stradmann, Johannes Schemmel, Friedemann Zenke |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1820193128 | ||
| 003 | DE-627 | ||
| 005 | 20230118135917.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 221027s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TNNLS.2020.3044364 |2 doi | |
| 035 | |a (DE-627)1820193128 | ||
| 035 | |a (DE-599)KXP1820193128 | ||
| 035 | |a (OCoLC)1361693673 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 29 |2 sdnb | ||
| 100 | 1 | |a Cramer, Benjamin |d 1993- |e VerfasserIn |0 (DE-588)1125028068 |0 (DE-627)879345616 |0 (DE-576)483278572 |4 aut | |
| 245 | 1 | 4 | |a The Heidelberg spiking data sets for the systematic evaluation of spiking neural networks |c Benjamin Cramer, Yannik Stradmann, Johannes Schemmel, Friedemann Zenke |
| 264 | 1 | |c July 2022 | |
| 300 | |a 14 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 27.10.2022 | ||
| 520 | |a Spiking neural networks are the basis of versatile and power-efficient information processing in the brain. Although we currently lack a detailed understanding of how these networks compute, recently developed optimization techniques allow us to instantiate increasingly complex functional spiking neural networks in-silico. These methods hold the promise to build more efficient non-von-Neumann computing hardware and will offer new vistas in the quest of unraveling brain circuit function. To accelerate the development of such methods, objective ways to compare their performance are indispensable. Presently, however, there are no widely accepted means for comparing the computational performance of spiking neural networks. To address this issue, we introduce two spike-based classification data sets, broadly applicable to benchmark both software and neuromorphic hardware implementations of spiking neural networks. To accomplish this, we developed a general audio-to-spiking conversion procedure inspired by neurophysiology. Furthermore, we applied this conversion to an existing and a novel speech data set. The latter is the free, high-fidelity, and word-level aligned Heidelberg digit data set that we created specifically for this study. By training a range of conventional and spiking classifiers, we show that leveraging spike timing information within these data sets is essential for good classification accuracy. These results serve as the first reference for future performance comparisons of spiking neural networks. | ||
| 650 | 4 | |a Audio | |
| 650 | 4 | |a benchmark | |
| 650 | 4 | |a Benchmark testing | |
| 650 | 4 | |a Biological neural networks | |
| 650 | 4 | |a classification | |
| 650 | 4 | |a data set | |
| 650 | 4 | |a Encoding | |
| 650 | 4 | |a Licenses | |
| 650 | 4 | |a neuromorphic computing | |
| 650 | 4 | |a spiking neural networks | |
| 650 | 4 | |a spoken digits | |
| 650 | 4 | |a surrogate gradients | |
| 650 | 4 | |a Task analysis | |
| 650 | 4 | |a Training | |
| 650 | 4 | |a Voltage control | |
| 700 | 1 | |a Stradmann, Yannik |e VerfasserIn |0 (DE-588)1181379393 |0 (DE-627)1662664249 |4 aut | |
| 700 | 1 | |a Schemmel, Johannes |e VerfasserIn |0 (DE-588)1025834607 |0 (DE-627)72488291X |0 (DE-576)370821440 |4 aut | |
| 700 | 1 | |a Zenke, Friedemann |e VerfasserIn |0 (DE-588)1219170976 |0 (DE-627)173495213X |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |a Institute of Electrical and Electronics Engineers |t IEEE transactions on neural networks and learning systems |d [New York, NY] : IEEE, 2012 |g 33(2022), 7, Seite 2744-2757 |h Online-Ressource |w (DE-627)68207084X |w (DE-600)2644189-5 |w (DE-576)356322246 |x 2162-2388 |7 nnas |
| 773 | 1 | 8 | |g volume:33 |g year:2022 |g number:7 |g pages:2744-2757 |g extent:14 |a The Heidelberg spiking data sets for the systematic evaluation of spiking neural networks |
| 856 | 4 | 0 | |u https://doi.org/10.1109/TNNLS.2020.3044364 |x Resolving-System |x Verlag |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://ieeexplore.ieee.org/document/9311226 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20221027 | ||
| 993 | |a Article | ||
| 994 | |a 2022 | ||
| 998 | |g 1025834607 |a Schemmel, Johannes |m 1025834607:Schemmel, Johannes |d 130000 |d 130700 |e 130000PS1025834607 |e 130700PS1025834607 |k 0/130000/ |k 1/130000/130700/ |p 3 | ||
| 998 | |g 1181379393 |a Stradmann, Yannik |m 1181379393:Stradmann, Yannik |d 130000 |d 130700 |e 130000PS1181379393 |e 130700PS1181379393 |k 0/130000/ |k 1/130000/130700/ |p 2 | ||
| 998 | |g 1125028068 |a Cramer, Benjamin |m 1125028068:Cramer, Benjamin |d 130000 |d 130700 |e 130000PC1125028068 |e 130700PC1125028068 |k 0/130000/ |k 1/130000/130700/ |p 1 |x j | ||
| 999 | |a KXP-PPN1820193128 |e 4202788451 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"person":[{"family":"Cramer","display":"Cramer, Benjamin","given":"Benjamin","role":"aut"},{"family":"Stradmann","display":"Stradmann, Yannik","given":"Yannik","role":"aut"},{"role":"aut","given":"Johannes","display":"Schemmel, Johannes","family":"Schemmel"},{"family":"Zenke","display":"Zenke, Friedemann","given":"Friedemann","role":"aut"}],"relHost":[{"part":{"year":"2022","extent":"14","pages":"2744-2757","text":"33(2022), 7, Seite 2744-2757","issue":"7","volume":"33"},"titleAlt":[{"title":"Neural networks and learning systems"},{"title":"Transactions on neural networks and learning systems"}],"disp":"Institute of Electrical and Electronics EngineersIEEE transactions on neural networks and learning systems","language":["eng"],"title":[{"title":"IEEE transactions on neural networks and learning systems","title_sort":"IEEE transactions on neural networks and learning systems"}],"note":["Gesehen am 02.02.12"],"pubHistory":["23.2012 -"],"recId":"68207084X","origin":[{"publisher":"IEEE","dateIssuedDisp":"2012-","dateIssuedKey":"2012","publisherPlace":"[New York, NY]"}],"id":{"eki":["68207084X"],"zdb":["2644189-5"],"issn":["2162-2388"]},"corporate":[{"role":"aut","display":"Institute of Electrical and Electronics Engineers"}],"name":{"displayForm":["Institute of Electrical and Electronics Engineers"]},"type":{"media":"Online-Ressource","bibl":"periodical"},"physDesc":[{"extent":"Online-Ressource"}]}],"recId":"1820193128","language":["eng"],"note":["Gesehen am 27.10.2022"],"title":[{"title_sort":"Heidelberg spiking data sets for the systematic evaluation of spiking neural networks","title":"The Heidelberg spiking data sets for the systematic evaluation of spiking neural networks"}],"origin":[{"dateIssuedDisp":"July 2022","dateIssuedKey":"2022"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"physDesc":[{"extent":"14 S."}],"id":{"eki":["1820193128"],"doi":["10.1109/TNNLS.2020.3044364"]},"name":{"displayForm":["Benjamin Cramer, Yannik Stradmann, Johannes Schemmel, Friedemann Zenke"]}} | ||
| SRT | |a CRAMERBENJHEIDELBERG2022 | ||