Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition
Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Li, Mian [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2021 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Neural computing & applications - Springer London, 1993, 34(2021), 1 vom: 07. Aug., Seite 319-331 |
|---|---|
| Übergeordnetes Werk: |
volume:34 ; year:2021 ; number:1 ; day:07 ; month:08 ; pages:319-331 |
| Links: |
|---|
| DOI / URN: |
10.1007/s00521-021-06361-4 |
|---|
| Katalog-ID: |
OLC2077769564 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2077769564 | ||
| 003 | DE-627 | ||
| 005 | 20230505191350.0 | ||
| 007 | tu | ||
| 008 | 221220s2021 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00521-021-06361-4 |2 doi | |
| 035 | |a (DE-627)OLC2077769564 | ||
| 035 | |a (DE-He213)s00521-021-06361-4-p | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |q VZ |
| 100 | 1 | |a Li, Mian |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 500 | |a © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021 | ||
| 520 | |a Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns. | ||
| 650 | 4 | |a Memristive circuit | |
| 650 | 4 | |a Competitive Neural Network | |
| 650 | 4 | |a Unsupervised learning | |
| 650 | 4 | |a Winner-take-all | |
| 650 | 4 | |a Pattern recognition | |
| 700 | 1 | |a Hong, Qinghui |4 aut | |
| 700 | 1 | |a Wang, Xiaoping |0 (orcid)0000-0002-4909-8286 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Neural computing & applications |d Springer London, 1993 |g 34(2021), 1 vom: 07. Aug., Seite 319-331 |w (DE-627)165669608 |w (DE-600)1136944-9 |w (DE-576)032873050 |x 0941-0643 |7 nnns |
| 773 | 1 | 8 | |g volume:34 |g year:2021 |g number:1 |g day:07 |g month:08 |g pages:319-331 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s00521-021-06361-4 |z lizenzpflichtig |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_4277 | ||
| 951 | |a AR | ||
| 952 | |d 34 |j 2021 |e 1 |b 07 |c 08 |h 319-331 | ||
| author_variant |
m l ml q h qh x w xw |
|---|---|
| matchkey_str |
article:09410643:2021----::ersobsdiciipeettoocmeiieerlewrbsdnnienuevsdeba |
| hierarchy_sort_str |
2021 |
| publishDate |
2021 |
| allfields |
10.1007/s00521-021-06361-4 doi (DE-627)OLC2077769564 (DE-He213)s00521-021-06361-4-p DE-627 ger DE-627 rakwb eng 004 VZ Li, Mian verfasserin aut Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021 Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns. Memristive circuit Competitive Neural Network Unsupervised learning Winner-take-all Pattern recognition Hong, Qinghui aut Wang, Xiaoping (orcid)0000-0002-4909-8286 aut Enthalten in Neural computing & applications Springer London, 1993 34(2021), 1 vom: 07. Aug., Seite 319-331 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2021 number:1 day:07 month:08 pages:319-331 https://doi.org/10.1007/s00521-021-06361-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2021 1 07 08 319-331 |
| spelling |
10.1007/s00521-021-06361-4 doi (DE-627)OLC2077769564 (DE-He213)s00521-021-06361-4-p DE-627 ger DE-627 rakwb eng 004 VZ Li, Mian verfasserin aut Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021 Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns. Memristive circuit Competitive Neural Network Unsupervised learning Winner-take-all Pattern recognition Hong, Qinghui aut Wang, Xiaoping (orcid)0000-0002-4909-8286 aut Enthalten in Neural computing & applications Springer London, 1993 34(2021), 1 vom: 07. Aug., Seite 319-331 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2021 number:1 day:07 month:08 pages:319-331 https://doi.org/10.1007/s00521-021-06361-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2021 1 07 08 319-331 |
| allfields_unstemmed |
10.1007/s00521-021-06361-4 doi (DE-627)OLC2077769564 (DE-He213)s00521-021-06361-4-p DE-627 ger DE-627 rakwb eng 004 VZ Li, Mian verfasserin aut Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021 Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns. Memristive circuit Competitive Neural Network Unsupervised learning Winner-take-all Pattern recognition Hong, Qinghui aut Wang, Xiaoping (orcid)0000-0002-4909-8286 aut Enthalten in Neural computing & applications Springer London, 1993 34(2021), 1 vom: 07. Aug., Seite 319-331 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2021 number:1 day:07 month:08 pages:319-331 https://doi.org/10.1007/s00521-021-06361-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2021 1 07 08 319-331 |
| allfieldsGer |
10.1007/s00521-021-06361-4 doi (DE-627)OLC2077769564 (DE-He213)s00521-021-06361-4-p DE-627 ger DE-627 rakwb eng 004 VZ Li, Mian verfasserin aut Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021 Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns. Memristive circuit Competitive Neural Network Unsupervised learning Winner-take-all Pattern recognition Hong, Qinghui aut Wang, Xiaoping (orcid)0000-0002-4909-8286 aut Enthalten in Neural computing & applications Springer London, 1993 34(2021), 1 vom: 07. Aug., Seite 319-331 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2021 number:1 day:07 month:08 pages:319-331 https://doi.org/10.1007/s00521-021-06361-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2021 1 07 08 319-331 |
| allfieldsSound |
10.1007/s00521-021-06361-4 doi (DE-627)OLC2077769564 (DE-He213)s00521-021-06361-4-p DE-627 ger DE-627 rakwb eng 004 VZ Li, Mian verfasserin aut Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition 2021 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021 Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns. Memristive circuit Competitive Neural Network Unsupervised learning Winner-take-all Pattern recognition Hong, Qinghui aut Wang, Xiaoping (orcid)0000-0002-4909-8286 aut Enthalten in Neural computing & applications Springer London, 1993 34(2021), 1 vom: 07. Aug., Seite 319-331 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:34 year:2021 number:1 day:07 month:08 pages:319-331 https://doi.org/10.1007/s00521-021-06361-4 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 AR 34 2021 1 07 08 319-331 |
| language |
English |
| source |
Enthalten in Neural computing & applications 34(2021), 1 vom: 07. Aug., Seite 319-331 volume:34 year:2021 number:1 day:07 month:08 pages:319-331 |
| sourceStr |
Enthalten in Neural computing & applications 34(2021), 1 vom: 07. Aug., Seite 319-331 volume:34 year:2021 number:1 day:07 month:08 pages:319-331 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Memristive circuit Competitive Neural Network Unsupervised learning Winner-take-all Pattern recognition |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
Neural computing & applications |
| authorswithroles_txt_mv |
Li, Mian @@aut@@ Hong, Qinghui @@aut@@ Wang, Xiaoping @@aut@@ |
| publishDateDaySort_date |
2021-08-07T00:00:00Z |
| hierarchy_top_id |
165669608 |
| dewey-sort |
14 |
| id |
OLC2077769564 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2077769564</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505191350.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2021 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00521-021-06361-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2077769564</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00521-021-06361-4-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Li, Mian</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Memristive circuit</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Competitive Neural Network</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Unsupervised learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Winner-take-all</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pattern recognition</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hong, Qinghui</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Xiaoping</subfield><subfield code="0">(orcid)0000-0002-4909-8286</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural computing & applications</subfield><subfield code="d">Springer London, 1993</subfield><subfield code="g">34(2021), 1 vom: 07. Aug., Seite 319-331</subfield><subfield code="w">(DE-627)165669608</subfield><subfield code="w">(DE-600)1136944-9</subfield><subfield code="w">(DE-576)032873050</subfield><subfield code="x">0941-0643</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:34</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:1</subfield><subfield code="g">day:07</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:319-331</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00521-021-06361-4</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">34</subfield><subfield code="j">2021</subfield><subfield code="e">1</subfield><subfield code="b">07</subfield><subfield code="c">08</subfield><subfield code="h">319-331</subfield></datafield></record></collection>
|
| author |
Li, Mian |
| spellingShingle |
Li, Mian ddc 004 misc Memristive circuit misc Competitive Neural Network misc Unsupervised learning misc Winner-take-all misc Pattern recognition Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition |
| authorStr |
Li, Mian |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)165669608 |
| format |
Article |
| dewey-ones |
004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0941-0643 |
| topic_title |
004 VZ Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition Memristive circuit Competitive Neural Network Unsupervised learning Winner-take-all Pattern recognition |
| topic |
ddc 004 misc Memristive circuit misc Competitive Neural Network misc Unsupervised learning misc Winner-take-all misc Pattern recognition |
| topic_unstemmed |
ddc 004 misc Memristive circuit misc Competitive Neural Network misc Unsupervised learning misc Winner-take-all misc Pattern recognition |
| topic_browse |
ddc 004 misc Memristive circuit misc Competitive Neural Network misc Unsupervised learning misc Winner-take-all misc Pattern recognition |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| hierarchy_parent_title |
Neural computing & applications |
| hierarchy_parent_id |
165669608 |
| dewey-tens |
000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Neural computing & applications |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 |
| title |
Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition |
| ctrlnum |
(DE-627)OLC2077769564 (DE-He213)s00521-021-06361-4-p |
| title_full |
Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition |
| author_sort |
Li, Mian |
| journal |
Neural computing & applications |
| journalStr |
Neural computing & applications |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2021 |
| contenttype_str_mv |
txt |
| container_start_page |
319 |
| author_browse |
Li, Mian Hong, Qinghui Wang, Xiaoping |
| container_volume |
34 |
| class |
004 VZ |
| format_se |
Aufsätze |
| author-letter |
Li, Mian |
| doi_str_mv |
10.1007/s00521-021-06361-4 |
| normlink |
(ORCID)0000-0002-4909-8286 |
| normlink_prefix_str_mv |
(orcid)0000-0002-4909-8286 |
| dewey-full |
004 |
| title_sort |
memristor-based circuit implementation of competitive neural network based on online unsupervised hebbian learning rule for pattern recognition |
| title_auth |
Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition |
| abstract |
Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021 |
| abstractGer |
Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021 |
| abstract_unstemmed |
Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2018 GBV_ILN_4277 |
| container_issue |
1 |
| title_short |
Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition |
| url |
https://doi.org/10.1007/s00521-021-06361-4 |
| remote_bool |
false |
| author2 |
Hong, Qinghui Wang, Xiaoping |
| author2Str |
Hong, Qinghui Wang, Xiaoping |
| ppnlink |
165669608 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s00521-021-06361-4 |
| up_date |
2024-07-03T17:13:02.325Z |
| _version_ |
1803578803311607808 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">OLC2077769564</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230505191350.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">221220s2021 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00521-021-06361-4</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2077769564</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00521-021-06361-4-p</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Li, Mian</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Memristor-based circuit implementation of Competitive Neural Network based on online unsupervised Hebbian learning rule for pattern recognition</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2021</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In this paper, a Competitive Neural Network circuit based on voltage-controlled memristors is proposed, of which the synapse structure is one memristor (1M). The designed circuit consists of the forward calculation part and the weight updating part. The forward calculation part is designed according to the winner-take-all mechanism, in which the m-LIF model and PMOS transistors with switching characteristics are combined to achieve the lateral inhibition. The weight updating part is designed based on the Hebbian learning rule. By using the voltage controlled switches, only the synaptic memristors connected to the winner output neuron obtained from the forward calculation part are adjusted. The whole circuit does not require the participation of CPU, FPGA or other microcontrollers, providing the possibility to realize computing-in-memory and parallel computing. We perform simulation experiments of unsupervised online learning of 5*3 pixels patterns and 28*28 pixels patterns based on the designed circuit in PSPICE. The changing trend of the network weights during the training phase and the high recognition accuracy in the recognition phase verify the network can effectively learn and recognize different patterns.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Memristive circuit</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Competitive Neural Network</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Unsupervised learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Winner-take-all</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pattern recognition</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hong, Qinghui</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Xiaoping</subfield><subfield code="0">(orcid)0000-0002-4909-8286</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Neural computing & applications</subfield><subfield code="d">Springer London, 1993</subfield><subfield code="g">34(2021), 1 vom: 07. Aug., Seite 319-331</subfield><subfield code="w">(DE-627)165669608</subfield><subfield code="w">(DE-600)1136944-9</subfield><subfield code="w">(DE-576)032873050</subfield><subfield code="x">0941-0643</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:34</subfield><subfield code="g">year:2021</subfield><subfield code="g">number:1</subfield><subfield code="g">day:07</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:319-331</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00521-021-06361-4</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2018</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4277</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">34</subfield><subfield code="j">2021</subfield><subfield code="e">1</subfield><subfield code="b">07</subfield><subfield code="c">08</subfield><subfield code="h">319-331</subfield></datafield></record></collection>
|
| score |
7.4000263 |