Eintrag weiter verarbeiten
Spiking neurons with short-term synaptic plasticity form superior generative networks
Gespeichert in:
Veröffentlicht in: | Scientific reports 8(2018) Artikel-Nummer 10651, 11 Seiten |
---|---|
Personen und Körperschaften: | , , , , , |
Titel: | Spiking neurons with short-term synaptic plasticity form superior generative networks/ Luziwei Leng, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier & Mihai A. Petrovici |
Format: | E-Book-Kapitel |
Sprache: | Englisch |
veröffentlicht: |
13 July 2018
|
Gesamtaufnahme: |
: Scientific reports, 8(2018) Artikel-Nummer 10651, 11 Seiten
, volume:8 |
Quelle: | Verbunddaten SWB Lizenzfreie Online-Ressourcen |
LEADER | 03996caa a2200625 4500 | ||
---|---|---|---|
001 | 0-1578092760 | ||
003 | DE-627 | ||
005 | 20210815182327.0 | ||
007 | cr uuu---uuuuu | ||
008 | 180731s2018 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1038/s41598-018-28999-2 |2 doi | |
035 | |a (DE-627)1578092760 | ||
035 | |a (DE-576)508092760 | ||
035 | |a (DE-599)BSZ508092760 | ||
035 | |a (OCoLC)1264004437 | ||
040 | |a DE-627 |b ger |c DE-627 |e rda | ||
041 | |a eng | ||
100 | 1 | |a Leng, Luziwei |d 1990- |e VerfasserIn |0 (DE-588)1163617431 |0 (DE-627)1027932908 |0 (DE-576)508090601 |4 aut | |
245 | 1 | 0 | |a Spiking neurons with short-term synaptic plasticity form superior generative networks |c Luziwei Leng, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier & Mihai A. Petrovici |
264 | 1 | |c 13 July 2018 | |
300 | |a 11 | ||
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 31.07.2018 | ||
520 | |a Spiking networks that perform probabilistic inference have been proposed both as models of cortical computation and as candidates for solving problems in machine learning. However, the evidence for spike-based computation being in any way superior to non-spiking alternatives remains scarce. We propose that short-term synaptic plasticity can provide spiking networks with distinct computational advantages compared to their classical counterparts. When learning from high-dimensional, diverse datasets, deep attractors in the energy landscape often cause mixing problems to the sampling process. Classical algorithms solve this problem by employing various tempering techniques, which are both computationally demanding and require global state updates. We demonstrate how similar results can be achieved in spiking networks endowed with local short-term synaptic plasticity. Additionally, we discuss how these networks can even outperform tempering-based approaches when the training data is imbalanced. We thereby uncover a powerful computational property of the biologically inspired, local, spike-triggered synaptic dynamics based simply on a limited pool of synaptic resources, which enables them to deal with complex sensory data. | ||
700 | 1 | |a Breitwieser, Oliver |d 1987- |e VerfasserIn |0 (DE-588)1163617652 |0 (DE-627)1027933408 |0 (DE-576)508090997 |4 aut | |
700 | 1 | |a Bytschok, Ilja |e VerfasserIn |0 (DE-588)1072021145 |0 (DE-627)826788904 |0 (DE-576)433488778 |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 Meier, Karlheinz |d 1955-2018 |e VerfasserIn |0 (DE-588)1025835115 |0 (DE-627)724884114 |0 (DE-576)370822269 |4 aut | |
700 | 1 | |a Petrovici, Mihai A. |e VerfasserIn |0 (DE-588)1072021005 |0 (DE-627)826788823 |0 (DE-576)433488700 |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Scientific reports |d [London] : Macmillan Publishers Limited, part of Springer Nature, 2011 |g 8(2018) Artikel-Nummer 10651, 11 Seiten |h Online-Ressource |w (DE-627)663366712 |w (DE-600)2615211-3 |w (DE-576)346641179 |x 2045-2322 |7 nnns |
773 | 1 | 8 | |g volume:8 |g year:2018 |g extent:11 |
856 | 4 | 0 | |u http://dx.doi.org/10.1038/s41598-018-28999-2 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
856 | 4 | 0 | |u https://www.nature.com/articles/s41598-018-28999-2 |x Verlag |z kostenfrei |3 Volltext |
936 | u | w | |d 8 |j 2018 |g 11 |y 8(2018) Artikel-Nummer 10651, 11 Seiten |
951 | |a AR | ||
856 | 4 | 0 | |u http://dx.doi.org/10.1038/s41598-018-28999-2 |9 LFER |
852 | |a LFER |z 2018-08-13T00:00:00Z | ||
970 | |c OD | ||
971 | |c EBOOK | ||
972 | |c EBOOK | ||
973 | |c Aufsatz | ||
935 | |a lfer | ||
900 | |a Leng, L. | ||
900 | |a Breitwieser, Oliver Julien | ||
900 | |a Petrovici, Mihai Alexandru | ||
900 | |a Petrovici, M. A. | ||
900 | |a Petrovici, Mihai | ||
900 | |a Petrovici, M. | ||
900 | |a Meier, K. | ||
900 | |a Schemmel, J. | ||
951 | |b XB-CN | ||
951 | |b XA-DE | ||
980 | |a 1578092760 |b 0 |k 1578092760 |o 508092760 |c lfer |
openURL |
url_ver=Z39.88-2004&ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fvufind.svn.sourceforge.net%3Agenerator&rft.title=Spiking+neurons+with+short-term+synaptic+plasticity+form+superior+generative+networks&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.creator=Leng%2C+Luziwei&rft.pub=&rft.format=Journal&rft.language=English&rft.issn=2045-2322 |
---|
_version_ | 1757949783879712768 |
---|---|
access_facet | Electronic Resources |
author | Leng, Luziwei, Breitwieser, Oliver, Bytschok, Ilja, Schemmel, Johannes, Meier, Karlheinz, Petrovici, Mihai A. |
author_facet | Leng, Luziwei, Breitwieser, Oliver, Bytschok, Ilja, Schemmel, Johannes, Meier, Karlheinz, Petrovici, Mihai A. |
author_role | aut, aut, aut, aut, aut, aut |
author_sort | Leng, Luziwei 1990- |
author_variant | l l ll, o b ob, i b ib, j s js, k m km, m a p ma map |
callnumber-sort | |
collection | lfer |
container_reference | 8(2018) Artikel-Nummer 10651, 11 Seiten |
container_title | Scientific reports |
contents | Spiking networks that perform probabilistic inference have been proposed both as models of cortical computation and as candidates for solving problems in machine learning. However, the evidence for spike-based computation being in any way superior to non-spiking alternatives remains scarce. We propose that short-term synaptic plasticity can provide spiking networks with distinct computational advantages compared to their classical counterparts. When learning from high-dimensional, diverse datasets, deep attractors in the energy landscape often cause mixing problems to the sampling process. Classical algorithms solve this problem by employing various tempering techniques, which are both computationally demanding and require global state updates. We demonstrate how similar results can be achieved in spiking networks endowed with local short-term synaptic plasticity. Additionally, we discuss how these networks can even outperform tempering-based approaches when the training data is imbalanced. We thereby uncover a powerful computational property of the biologically inspired, local, spike-triggered synaptic dynamics based simply on a limited pool of synaptic resources, which enables them to deal with complex sensory data. |
ctrlnum | (DE-627)1578092760, (DE-576)508092760, (DE-599)BSZ508092760, (OCoLC)1264004437 |
doi_str_mv | 10.1038/s41598-018-28999-2 |
facet_avail | Online, Free |
finc_class_facet | not assigned |
finc_id_str | 0021207298 |
footnote | Gesehen am 31.07.2018 |
format | ElectronicBookComponentPart |
format_access_txtF_mv | Article, E-Article |
format_de105 | Ebook |
format_de14 | Article, E-Article |
format_de15 | Article, E-Article |
format_del152 | Buch |
format_detail_txtF_mv | text-online-monograph-child |
format_dezi4 | e-Book |
format_finc | Article, E-Article |
format_legacy | ElectronicBookPart |
format_strict_txtF_mv | E-Article |
geogr_code | not assigned |
geogr_code_person | China, Germany |
hierarchy_parent_id | 0-663366712 |
hierarchy_parent_title | Scientific reports |
hierarchy_sequence | 8(2018) Artikel-Nummer 10651, 11 Seiten |
hierarchy_top_id | 0-663366712 |
hierarchy_top_title | Scientific reports |
id | 0-1578092760 |
illustrated | Not Illustrated |
imprint | 13 July 2018 |
imprint_str_mv | 13 July 2018 |
institution | DE-D117, DE-105, LFER, DE-Ch1, DE-15, DE-14, DE-Zwi2 |
is_hierarchy_id | 0-1578092760 |
is_hierarchy_title | Spiking neurons with short-term synaptic plasticity form superior generative networks |
isil_str_mv | LFER |
issn | 2045-2322 |
kxp_id_str | 1578092760 |
language | English |
last_indexed | 2023-02-16T01:39:16.891Z |
marc024a_ct_mv | 10.1038/s41598-018-28999-2 |
match_str | leng2018spikingneuronswithshorttermsynapticplasticityformsuperiorgenerativenetworks |
mega_collection | Verbunddaten SWB, Lizenzfreie Online-Ressourcen |
misc_de105 | EBOOK |
multipart_link | 346641179 |
multipart_part | (346641179)8(2018) Artikel-Nummer 10651, 11 Seiten |
names_id_str_mv | (DE-588)1163617431, (DE-627)1027932908, (DE-576)508090601, (DE-588)1163617652, (DE-627)1027933408, (DE-576)508090997, (DE-588)1072021145, (DE-627)826788904, (DE-576)433488778, (DE-588)1025834607, (DE-627)72488291X, (DE-576)370821440, (DE-588)1025835115, (DE-627)724884114, (DE-576)370822269, (DE-588)1072021005, (DE-627)826788823, (DE-576)433488700 |
oclc_num | 1264004437 |
physical | 11 |
publishDate | 13 July 2018 |
publishDateSort | 2018 |
publishPlace | |
publisher | |
record_format | marcfinc |
record_id | 508092760 |
recordtype | marcfinc |
rvk_facet | No subject assigned |
source_id | 0 |
spelling | Leng, Luziwei 1990- VerfasserIn (DE-588)1163617431 (DE-627)1027932908 (DE-576)508090601 aut, Spiking neurons with short-term synaptic plasticity form superior generative networks Luziwei Leng, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier & Mihai A. Petrovici, 13 July 2018, 11, Text txt rdacontent, Computermedien c rdamedia, Online-Ressource cr rdacarrier, Gesehen am 31.07.2018, Spiking networks that perform probabilistic inference have been proposed both as models of cortical computation and as candidates for solving problems in machine learning. However, the evidence for spike-based computation being in any way superior to non-spiking alternatives remains scarce. We propose that short-term synaptic plasticity can provide spiking networks with distinct computational advantages compared to their classical counterparts. When learning from high-dimensional, diverse datasets, deep attractors in the energy landscape often cause mixing problems to the sampling process. Classical algorithms solve this problem by employing various tempering techniques, which are both computationally demanding and require global state updates. We demonstrate how similar results can be achieved in spiking networks endowed with local short-term synaptic plasticity. Additionally, we discuss how these networks can even outperform tempering-based approaches when the training data is imbalanced. We thereby uncover a powerful computational property of the biologically inspired, local, spike-triggered synaptic dynamics based simply on a limited pool of synaptic resources, which enables them to deal with complex sensory data., Breitwieser, Oliver 1987- VerfasserIn (DE-588)1163617652 (DE-627)1027933408 (DE-576)508090997 aut, Bytschok, Ilja VerfasserIn (DE-588)1072021145 (DE-627)826788904 (DE-576)433488778 aut, Schemmel, Johannes VerfasserIn (DE-588)1025834607 (DE-627)72488291X (DE-576)370821440 aut, Meier, Karlheinz 1955-2018 VerfasserIn (DE-588)1025835115 (DE-627)724884114 (DE-576)370822269 aut, Petrovici, Mihai A. VerfasserIn (DE-588)1072021005 (DE-627)826788823 (DE-576)433488700 aut, Enthalten in Scientific reports [London] : Macmillan Publishers Limited, part of Springer Nature, 2011 8(2018) Artikel-Nummer 10651, 11 Seiten Online-Ressource (DE-627)663366712 (DE-600)2615211-3 (DE-576)346641179 2045-2322 nnns, volume:8 year:2018 extent:11, http://dx.doi.org/10.1038/s41598-018-28999-2 Verlag Resolving-System kostenfrei Volltext, https://www.nature.com/articles/s41598-018-28999-2 Verlag kostenfrei Volltext, http://dx.doi.org/10.1038/s41598-018-28999-2 LFER, LFER 2018-08-13T00:00:00Z |
spellingShingle | Leng, Luziwei, Breitwieser, Oliver, Bytschok, Ilja, Schemmel, Johannes, Meier, Karlheinz, Petrovici, Mihai A., Spiking neurons with short-term synaptic plasticity form superior generative networks, Spiking networks that perform probabilistic inference have been proposed both as models of cortical computation and as candidates for solving problems in machine learning. However, the evidence for spike-based computation being in any way superior to non-spiking alternatives remains scarce. We propose that short-term synaptic plasticity can provide spiking networks with distinct computational advantages compared to their classical counterparts. When learning from high-dimensional, diverse datasets, deep attractors in the energy landscape often cause mixing problems to the sampling process. Classical algorithms solve this problem by employing various tempering techniques, which are both computationally demanding and require global state updates. We demonstrate how similar results can be achieved in spiking networks endowed with local short-term synaptic plasticity. Additionally, we discuss how these networks can even outperform tempering-based approaches when the training data is imbalanced. We thereby uncover a powerful computational property of the biologically inspired, local, spike-triggered synaptic dynamics based simply on a limited pool of synaptic resources, which enables them to deal with complex sensory data. |
swb_id_str | 508092760 |
title | Spiking neurons with short-term synaptic plasticity form superior generative networks |
title_auth | Spiking neurons with short-term synaptic plasticity form superior generative networks |
title_full | Spiking neurons with short-term synaptic plasticity form superior generative networks Luziwei Leng, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier & Mihai A. Petrovici |
title_fullStr | Spiking neurons with short-term synaptic plasticity form superior generative networks Luziwei Leng, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier & Mihai A. Petrovici |
title_full_unstemmed | Spiking neurons with short-term synaptic plasticity form superior generative networks Luziwei Leng, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier & Mihai A. Petrovici |
title_in_hierarchy | Spiking neurons with short-term synaptic plasticity form superior generative networks / Luziwei Leng, Roman Martel, Oliver Breitwieser, Ilja Bytschok, Walter Senn, Johannes Schemmel, Karlheinz Meier & Mihai A. Petrovici, |
title_short | Spiking neurons with short-term synaptic plasticity form superior generative networks |
title_sort | spiking neurons with short term synaptic plasticity form superior generative networks |
url | http://dx.doi.org/10.1038/s41598-018-28999-2, https://www.nature.com/articles/s41598-018-28999-2 |