Comparing Loihi with a SpiNNaker 2 prototype on low-latency keyword spotting and adaptive robotic control
Abstract We implemented two neural network based benchmark tasks on a prototype chip of the second-generation SpiNNaker (SpiNNaker 2) neuromorphic system: keyword spotting and adaptive robotic control. Keyword spotting is commonly used in smart speakers to listen for wake words, and adaptive control...
Saved in:
| Published in | Neuromorphic computing and engineering Vol. 1; no. 1; p. 14002 |
|---|---|
| Main Authors | , , , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
IOP Publishing
01.09.2021
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 2634-4386 2634-4386 |
| DOI | 10.1088/2634-4386/abf150 |
Cover
| Abstract | Abstract We implemented two neural network based benchmark tasks on a prototype chip of the second-generation SpiNNaker (SpiNNaker 2) neuromorphic system: keyword spotting and adaptive robotic control. Keyword spotting is commonly used in smart speakers to listen for wake words, and adaptive control is used in robotic applications to adapt to unknown dynamics in an online fashion. We highlight the benefit of a multiply-accumulate (MAC) array in the SpiNNaker 2 prototype which is ordinarily used in rate-based machine learning networks when employed in a neuromorphic, spiking context. In addition, the same benchmark tasks have been implemented on the Loihi neuromorphic chip, giving a side-by-side comparison regarding power consumption and computation time. While Loihi shows better efficiency when less complicated vector-matrix multiplication is involved, with the MAC array, the SpiNNaker 2 prototype shows better efficiency when high dimensional vector-matrix multiplication is involved. NRC publication: Yes |
|---|---|
| AbstractList | Abstract We implemented two neural network based benchmark tasks on a prototype chip of the second-generation SpiNNaker (SpiNNaker 2) neuromorphic system: keyword spotting and adaptive robotic control. Keyword spotting is commonly used in smart speakers to listen for wake words, and adaptive control is used in robotic applications to adapt to unknown dynamics in an online fashion. We highlight the benefit of a multiply-accumulate (MAC) array in the SpiNNaker 2 prototype which is ordinarily used in rate-based machine learning networks when employed in a neuromorphic, spiking context. In addition, the same benchmark tasks have been implemented on the Loihi neuromorphic chip, giving a side-by-side comparison regarding power consumption and computation time. While Loihi shows better efficiency when less complicated vector-matrix multiplication is involved, with the MAC array, the SpiNNaker 2 prototype shows better efficiency when high dimensional vector-matrix multiplication is involved. We implemented two neural network based benchmark tasks on a prototype chip of the second-generation SpiNNaker (SpiNNaker 2) neuromorphic system: keyword spotting and adaptive robotic control. Keyword spotting is commonly used in smart speakers to listen for wake words, and adaptive control is used in robotic applications to adapt to unknown dynamics in an online fashion. We highlight the benefit of a multiply-accumulate (MAC) array in the SpiNNaker 2 prototype which is ordinarily used in rate-based machine learning networks when employed in a neuromorphic, spiking context. In addition, the same benchmark tasks have been implemented on the Loihi neuromorphic chip, giving a side-by-side comparison regarding power consumption and computation time. While Loihi shows better efficiency when less complicated vector-matrix multiplication is involved, with the MAC array, the SpiNNaker 2 prototype shows better efficiency when high dimensional vector-matrix multiplication is involved. |
| Author | Höppner, Sebastian Kelber, Florian Furber, Steve Mayr, Christian Stewart, Terrence C Partzsch, Johannes Eliasmith, Chris Vogginger, Bernhard Yan, Yexin Choo, Xuan |
| Author_xml | – sequence: 1 fullname: Yan, Yexin – sequence: 2 fullname: Stewart, Terrence C – sequence: 3 fullname: Choo, Xuan – sequence: 4 fullname: Vogginger, Bernhard – sequence: 5 fullname: Partzsch, Johannes – sequence: 6 fullname: Höppner, Sebastian – sequence: 7 fullname: Kelber, Florian – sequence: 8 fullname: Eliasmith, Chris – sequence: 9 fullname: Furber, Steve – sequence: 10 fullname: Mayr, Christian |
| BookMark | eNp9kE1LJDEQhoMo6LrePeYPtCadj04fZVBXGPSwu-dQ-dI4bdKkg8P8e7sdGZY9eEmFlzxVlecHOk45eYQuKbmiRKnrVjLecKbkNZhABTlCZ4fo-J_7KbqYpldCSNt1lEpxhuIqv41QYnrG6xxfIt7G-oIB_x7j4yNsfMEtHkuuue5Gj3PCQ942A1Sf7A5v_G6bi8PTmGtdWkByGByMNb57XLLJNVpsc6olDz_RSYBh8hdf9Rz9vbv9s_rVrJ_uH1Y368ayTtUm0JaR0FFnTced7EzPhWwFDwQCCwCqZZ4KIwO0zgllSS96Fji3lHBDpGTnSO772pKnqfigbaxQ47IFxEFTohdnepGiFyl672wGyX_gWOIblN13iNsjqVgLaf76gckQ58FTjTouRc8vtP08YJ-nWbvVRHZBCUc0BxU0tyRo1XOjad93pjXWCNmzD-hOlgU |
| CitedBy_id | crossref_primary_10_3389_fnins_2022_851774 crossref_primary_10_1038_s41467_024_44723_3 crossref_primary_10_3389_fnins_2024_1360122 crossref_primary_10_3389_fnins_2022_1018006 crossref_primary_10_1088_2634_4386_ac4c38 crossref_primary_10_1038_s41586_024_08253_8 crossref_primary_10_3390_electronics12183964 crossref_primary_10_1109_TC_2022_3162708 crossref_primary_10_3389_fnins_2023_1190515 crossref_primary_10_3390_electronics13163203 crossref_primary_10_3390_s23063037 crossref_primary_10_1088_2634_4386_ac0a5b crossref_primary_10_3389_fnins_2022_867027 crossref_primary_10_3389_fnins_2023_1223262 crossref_primary_10_1109_JPROC_2023_3273520 crossref_primary_10_1038_s41467_022_28487_2 crossref_primary_10_1007_s11227_024_06826_y crossref_primary_10_1109_TMAG_2024_3403973 crossref_primary_10_3389_fnins_2024_1335422 crossref_primary_10_1038_s41598_023_47245_y crossref_primary_10_1088_2634_4386_ac889c crossref_primary_10_1088_2634_4386_ac889b crossref_primary_10_3389_fncom_2023_1148284 |
| Cites_doi | 10.1162/neco.2007.19.11.2881 10.1038/s41586-019-1677-2 10.1109/tcsi.2019.2911898 10.1109/tnnls.2016.2572164 10.1109/tbcas.2017.2759700 10.1109/tbcas.2016.2579164 10.1109/JPROC.2014.2313565 10.1109/jproc.2014.2304638 10.1177/027836498700600303 10.1126/science.1254642 10.1016/j.neuron.2016.10.046 10.3389/fnins.2018.00213 10.1371/journal.pone.0022885 10.3389/fnins.2015.00464 10.3389/fnbot.2020.568359 10.1038/s42256-020-0159-4 10.1109/jproc.2018.2881432 10.1038/s41586-019-1424-8 10.1109/mm.2018.112130359 10.1126/science.275.5297.213 10.1109/jproc.2017.2761740 10.1007/s11265-020-01556-9 10.1098/rspb.2016.2134 10.1109/TCSII.2019.2959544 10.1109/tbcas.2019.2928793 10.1109/tbcas.2014.2379294 10.1145/3320288.3320304 10.3389/fnins.2015.00141 10.1109/tbcas.2019.2906401 10.1126/science.1225266 10.1109/jetcas.2020.3032058 |
| ContentType | Journal Article |
| Copyright | Creative Commons, Attribution 4.0 International (CC BY 4.0) (https://creativecommons.org/licenses/by/4.0/) Creative Commons, Attribution 4.0 International (CC BY 4.0) (https://creativecommons.org/licenses/by/4.0/deed.fr) |
| Copyright_xml | – notice: Creative Commons, Attribution 4.0 International (CC BY 4.0) (https://creativecommons.org/licenses/by/4.0/) Creative Commons, Attribution 4.0 International (CC BY 4.0) (https://creativecommons.org/licenses/by/4.0/deed.fr) |
| DBID | -LJ GXV AAYXX CITATION |
| DOI | 10.1088/2634-4386/abf150 |
| DatabaseName | National Research Council Canada Archive CISTI Source CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Sciences Computer Science |
| EISSN | 2634-4386 |
| ExternalDocumentID | 10_1088_2634_4386_abf150 oai_cisti_icist_nrc_cnrc_ca_cistinparc_067f85d0_4a8f_4c0f_894b_1997b2bcb569 |
| GroupedDBID | -LJ ACHIP AEINN AKPSB ALMA_UNASSIGNED_HOLDINGS CJUJL GROUPED_DOAJ GXV M~E N5L O3W OK1 AAYXX ABHWH CITATION |
| ID | FETCH-LOGICAL-c378t-f1230f71dcb74d67b9456254f0af3faa823e15b6fa2dd58c09593f44c104b0663 |
| ISSN | 2634-4386 |
| IngestDate | Tue Jul 01 01:09:05 EDT 2025 Thu Apr 24 22:57:05 EDT 2025 Fri Sep 26 16:40:25 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c378t-f1230f71dcb74d67b9456254f0af3faa823e15b6fa2dd58c09593f44c104b0663 |
| ORCID | 0000-0002-4267-7015 |
| OpenAccessLink | https://iopscience.iop.org/article/10.1088/2634-4386/abf150/pdf |
| ParticipantIDs | crossref_citationtrail_10_1088_2634_4386_abf150 crossref_primary_10_1088_2634_4386_abf150 nrccanada_primary_oai_cisti_icist_nrc_cnrc_ca_cistinparc_067f85d0_4a8f_4c0f_894b_1997b2bcb569 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2021-09-01 |
| PublicationDateYYYYMMDD | 2021-09-01 |
| PublicationDate_xml | – month: 09 year: 2021 text: 2021-09-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Neuromorphic computing and engineering |
| PublicationYear | 2021 |
| Publisher | IOP Publishing |
| Publisher_xml | – name: IOP Publishing |
| References | Partzsch (nceabf150bib37) 2020; 92 Stromatias (nceabf150bib30) 2013 Furber (nceabf150bib11) 2014; 102 Walter (nceabf150bib20) 2020 Höppner (nceabf150bib10) 2021 DeWolf (nceabf150bib24) 2016; 283 Partzsch (nceabf150bib13) 2017 Park (nceabf150bib34) 2017; 28 Roy (nceabf150bib2) 2019; 575 Blouw (nceabf150bib4) 2019 DeWolf (nceabf150bib5) 2020 Höppner (nceabf150bib16) 2017 Carter (nceabf150bib18) 2016 Höppner (nceabf150bib17) 2019; 66 Stewart (nceabf150bib22) 2015; 9 Qiao (nceabf150bib39) 2015; 9 Davies (nceabf150bib3) 2018; 38 Neumärker (nceabf150bib15) 2016 Yan (nceabf150bib9) 2019; 13 Imam (nceabf150bib7) 2020; 2 Stewart (nceabf150bib8) 2020; 10 Sze (nceabf150bib1) 2017; 105 Höppner (nceabf150bib19) 2019 Mundy (nceabf150bib28) 2015 Varkey Benjamin (nceabf150bib32) 2014; 102 MacNeil (nceabf150bib23) 2011; 6 Eliasmith (nceabf150bib26) 2003 Amunts (nceabf150bib12) 2016; 92 Friedmann (nceabf150bib42) 2017; 11 Neckar (nceabf150bib33) 2019; 107 Slotine (nceabf150bib25) 1987; 6 Knight (nceabf150bib29) 2016 Hartmann (nceabf150bib43) 2010 Merolla (nceabf150bib31) 2014; 345 Moradi (nceabf150bib35) 2018; 12 Mayr (nceabf150bib6) 2019 Mikaitis (nceabf150bib14) 2018 Höppner (nceabf150bib21) 2019; 67 Wang (nceabf150bib38) 2018; 12 Pei (nceabf150bib36) 2019; 572 Mayr (nceabf150bib41) 2016; 10 Markram (nceabf150bib44) 1997; 275 Brader (nceabf150bib45) 2007; 19 Eliasmith (nceabf150bib27) 2012; 338 Frenkel (nceabf150bib40) Feb 2019; 13 |
| References_xml | – volume: 19 start-page: 2881 year: 2007 ident: nceabf150bib45 article-title: Learning real-world stimuli in a neural network with spike-driven synaptic dynamics publication-title: Neural Comput. doi: 10.1162/neco.2007.19.11.2881 – volume: 575 start-page: 607 year: 2019 ident: nceabf150bib2 article-title: Towards spike-based machine intelligence with neuromorphic computing publication-title: Nature doi: 10.1038/s41586-019-1677-2 – volume: 66 start-page: 2973 year: 2019 ident: nceabf150bib17 article-title: Dynamic power management for neuromorphic many-core systems publication-title: IEEE Trans. Circuits Syst. I doi: 10.1109/tcsi.2019.2911898 – volume: 28 start-page: 2408 year: 2017 ident: nceabf150bib34 article-title: Hierarchical address event routing for reconfigurable large-scale neuromorphic systems publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/tnnls.2016.2572164 – volume: 12 start-page: 106 year: 2018 ident: nceabf150bib35 article-title: A scalable multicore architecture with heterogeneous memory structures for dynamic neuromorphic asynchronous processors (dynaps) publication-title: IEEE Trans. Biomed. Circuits Syst. doi: 10.1109/tbcas.2017.2759700 – volume: 11 start-page: 128 year: 2017 ident: nceabf150bib42 article-title: Demonstrating hybrid learning in a flexible neuromorphic hardware system publication-title: IEEE Trans. Biomed. Circuits Syst. doi: 10.1109/tbcas.2016.2579164 – start-page: 37 year: 2018 ident: nceabf150bib14 article-title: Approximate fixed-point elementary function accelerator for the SpiNNaker-2 neuromorphic chip – volume: 102 start-page: 699 year: 2014 ident: nceabf150bib32 article-title: Neurogrid: a mixed-analog-digital multichip system for large-scale neural simulations publication-title: Proc. IEEE doi: 10.1109/JPROC.2014.2313565 – volume: 102 start-page: 652 year: 2014 ident: nceabf150bib11 article-title: The SpiNNaker project publication-title: Proc. IEEE doi: 10.1109/jproc.2014.2304638 – volume: 6 start-page: 49 year: 1987 ident: nceabf150bib25 article-title: On the adaptive control of robot manipulators publication-title: Int. J. Robot. Res. doi: 10.1177/027836498700600303 – start-page: 1 year: 2017 ident: nceabf150bib13 article-title: A fixed point exponential function accelerator for a neuromorphic many-core system – start-page: 1 year: 2015 ident: nceabf150bib28 article-title: An efficient SpiNNaker implementation of the neural engineering framework – volume: 345 start-page: 668 year: 2014 ident: nceabf150bib31 article-title: A million spiking-neuron integrated circuit with a scalable communication network and interface publication-title: Science doi: 10.1126/science.1254642 – volume: 92 start-page: 574 year: 2016 ident: nceabf150bib12 article-title: The human brain project: creating a European research infrastructure to decode the human brain publication-title: Neuron doi: 10.1016/j.neuron.2016.10.046 – start-page: 66 year: 2019 ident: nceabf150bib19 article-title: How to achieve world-leading energy efficiency using 22fdx with adaptive body biasing on an arm cortex-m4 iot soc – volume: 12 start-page: 213 year: 2018 ident: nceabf150bib38 article-title: An FPGA-based massively parallel neuromorphic cortex simulator publication-title: Front. Neurosci. doi: 10.3389/fnins.2018.00213 – start-page: 221 year: 2016 ident: nceabf150bib18 article-title: 22 nm FDSOI technology for emerging mobile, internet-of-things, and rf applications – volume: 6 year: 2011 ident: nceabf150bib23 article-title: Fine-tuning and the stability of recurrent neural networks publication-title: PLoS One doi: 10.1371/journal.pone.0022885 – start-page: 950 year: 2010 ident: nceabf150bib43 article-title: Highly integrated packet-based AER communication infrastructure with 3 gevent/s throughput – start-page: 1 year: 2016 ident: nceabf150bib15 article-title: True random number generation from bang-bang adpll jitter – year: 2019 ident: nceabf150bib6 article-title: SpiNNaker 2: a 10 million core processor system for brain simulation and machine learning – volume: 9 start-page: 464 year: 2015 ident: nceabf150bib22 article-title: Closed-loop neuromorphic benchmarks publication-title: Front. Neurosci. doi: 10.3389/fnins.2015.00464 – year: 2020 ident: nceabf150bib5 article-title: Nengo and low-power AI hardware for robust, embedded neurorobotics doi: 10.3389/fnbot.2020.568359 – volume: 2 start-page: 181 year: 2020 ident: nceabf150bib7 article-title: Rapid online learning and robust recall in a neuromorphic olfactory circuit publication-title: Nat. Mach. Intell. doi: 10.1038/s42256-020-0159-4 – start-page: 1 year: 2013 ident: nceabf150bib30 article-title: Power analysis of large-scale, real-time neural networks on SpiNNaker – volume: 107 start-page: 144 year: 2019 ident: nceabf150bib33 article-title: Braindrop: a mixed-signal neuromorphic architecture with a dynamical systems-based programming model publication-title: Proc. IEEE doi: 10.1109/jproc.2018.2881432 – start-page: 5210 year: 2016 ident: nceabf150bib29 article-title: Efficient SpiNNaker simulation of a heteroassociative memory using the neural engineering framework – volume: 572 start-page: 106 year: 2019 ident: nceabf150bib36 article-title: Towards artificial general intelligence with hybrid tianjic chip architecture publication-title: Nature doi: 10.1038/s41586-019-1424-8 – volume: 38 start-page: 82 year: 2018 ident: nceabf150bib3 article-title: Loihi: a neuromorphic manycore processor with on-chip learning publication-title: IEEE Micro doi: 10.1109/mm.2018.112130359 – volume: 275 start-page: 213 year: 1997 ident: nceabf150bib44 article-title: Regulation of synaptic efficacy by coincidence of postsynaptic APS and EPSPS publication-title: Science doi: 10.1126/science.275.5297.213 – year: 2003 ident: nceabf150bib26 – volume: 105 start-page: 2295 year: 2017 ident: nceabf150bib1 article-title: Efficient processing of deep neural networks: a tutorial and survey publication-title: Proc. IEEE doi: 10.1109/jproc.2017.2761740 – start-page: 1 year: 2020 ident: nceabf150bib20 article-title: A 0.55 V 6.3 μW/MHz Arm Cortex-M4 MCU with adaptive reverse body bias and single rail SRAM – volume: 92 start-page: 1303 year: 2020 ident: nceabf150bib37 article-title: Mean field approach for configuring population dynamics on a biohybrid neuromorphic system publication-title: J. Signal Process. Syst. doi: 10.1007/s11265-020-01556-9 – start-page: 1 year: 2017 ident: nceabf150bib16 article-title: Dynamic voltage and frequency scaling for neuromorphic many-core systems – volume: 283 start-page: 20162134 year: 2016 ident: nceabf150bib24 article-title: A spiking neural model of adaptive arm control publication-title: Proc. R. Soc. B. doi: 10.1098/rspb.2016.2134 – volume: 67 start-page: 2159 year: 2019 ident: nceabf150bib21 article-title: Adaptive body bias aware implementation for ultra-low-voltage designs in 22FDX technology publication-title: IEEE Trans. Circuits Syst. II doi: 10.1109/TCSII.2019.2959544 – volume: 13 start-page: 145 year: Feb 2019 ident: nceabf150bib40 article-title: A 0.086 mm2 12.7-pj/sop 64k-synapse 256-neuron online-learning digital spiking neuromorphic processor in 28 nm CMOS publication-title: IEEE Trans. Biomed. Circuits Syst. doi: 10.1109/tbcas.2019.2928793 – volume: 10 start-page: 243 year: 2016 ident: nceabf150bib41 article-title: A biological-realtime neuromorphic system in 28 nm CMOS using low-leakage switched capacitor circuits publication-title: IEEE Trans. Biomed. Circuits Syst. doi: 10.1109/tbcas.2014.2379294 – year: 2019 ident: nceabf150bib4 article-title: Benchmarking keyword spotting efficiency on neuromorphic hardware doi: 10.1145/3320288.3320304 – volume: 9 start-page: 141 year: 2015 ident: nceabf150bib39 article-title: A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128k synapses publication-title: Front. Neurosci. doi: 10.3389/fnins.2015.00141 – volume: 13 start-page: 579 year: 2019 ident: nceabf150bib9 article-title: Efficient reward-based structural plasticity on a SpiNNaker 2 prototype publication-title: IEEE Trans. Biomed. Circuits Syst. doi: 10.1109/tbcas.2019.2906401 – year: 2021 ident: nceabf150bib10 article-title: The SpiNNaker 2 processing element architecture for hybrid digital neuromorphic computing – volume: 338 start-page: 1202 year: 2012 ident: nceabf150bib27 article-title: A large-scale model of the functioning brain publication-title: Science doi: 10.1126/science.1225266 – volume: 10 start-page: 512 year: 2020 ident: nceabf150bib8 article-title: Online few-shot gesture learning on a neuromorphic processor publication-title: IEEE J. Emerg. Sel. Top. Circuits Syst. doi: 10.1109/jetcas.2020.3032058 |
| SSID | ssj0002771165 |
| Score | 2.3908954 |
| Snippet | Abstract We implemented two neural network based benchmark tasks on a prototype chip of the second-generation SpiNNaker (SpiNNaker 2) neuromorphic system:... We implemented two neural network based benchmark tasks on a prototype chip of the second-generation SpiNNaker (SpiNNaker 2) neuromorphic system: keyword... |
| SourceID | crossref nrccanada |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 14002 |
| SubjectTerms | adaptive robotic control keyword spotting Loihi MAC array neuromorphic computing SpiNNaker |
| Title | Comparing Loihi with a SpiNNaker 2 prototype on low-latency keyword spotting and adaptive robotic control |
| URI | https://nrc-publications.canada.ca/eng/view/object/?id=067f85d0-4a8f-4c0f-894b-1997b2bcb569 |
| Volume | 1 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lj9MwELbKcoALb8TyWPnABa1CE8d5HaECrZDoZbuoHJBlOzEbUZIqSrWIA3-Fv8qMnbhddkEsl7RynUmV-TIeT2a-IeQ5YypiIecBr2IT8DIPgzwtTJBzqQrFIhUarB1-P0-PTvi7ZbKcTH7uZC1tevVSf7-0ruR_tApjoFeskr2CZr1QGIDvoF84gobh-E86nrkmglin1Nan9VCodni8rudz-aXqDhnmX_WtjbOCmlftWbCSva22hIf3DEsFYVvrUp8ta2sp1zaXqGtVi1SuQyb7rgtr6Ty-tqAf-zs2hRhPr7bkht6auADrx-pb7WF4jAE7Vyq0qDpHc-uDtbPT1kZvl5stbj-0GBf_7ND1uuqakQtgjFewyCdkDWaNpTEgIx4JsC8ZG-3yBfg5GwtbQlukfdH6g8XEApdRGC5zykSO2PY81fZvS6BPTLSv5PNcoAyBMoSTcI1cZxk4Z5gb-mMbxGNZhvRF2MBwvOjwKhyETP3Y1Ak55_rcaDpt8_rkjj-zuENuDRsR-sqh6i6ZVM09cnts8kEHm3-f1B5k1IKMIsiopB5klFEPMto2dAdkdAAZHUFGASV0BBkdQEYHkD0gJ2_fLGZHwdCfI9BxlveBAa8nNFlUapXxMs1UYbfT3ITSxEbKnMVVlKjUSFaWSa4tCbbhXEchV-jqPiR7TdtUjwhFr7nQqcayac5NnCcwT8FWQurUwOx9Mh1vndADeT32UFmJP2lsn7zwZ6wdcctf5n7y2vCTkXdd4zoravwQMENoe5BuvIGbrwV4eyZPylBwmRvBdWhEXnAlMIFLMaVVkhaPr_BfnpCb26fmKdnru031DPzeXh3YeNGBReAvfQuxVg |
| linkProvider | ISSN International Centre |
| 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%3Ajournal&rft.genre=article&rft.atitle=Comparing+Loihi+with+a+SpiNNaker+2+prototype+on+low-latency+keyword+spotting+and+adaptive+robotic+control&rft.jtitle=Neuromorphic+computing+and+engineering&rft.au=Yan%2C+Yexin&rft.au=Stewart%2C+Terrence+C&rft.au=Choo%2C+Xuan&rft.au=Vogginger%2C+Bernhard&rft.date=2021-09-01&rft.issn=2634-4386&rft.eissn=2634-4386&rft.volume=1&rft.issue=1&rft.spage=14002&rft_id=info:doi/10.1088%2F2634-4386%2Fabf150&rft.externalDBID=n%2Fa&rft.externalDocID=10_1088_2634_4386_abf150 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2634-4386&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2634-4386&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2634-4386&client=summon |