A-optimal convolutional neural network
Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linea...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Yin, Zihong [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2016 |
|---|
| Schlagwörter: |
|---|
| Anmerkung: |
© The Natural Computing Applications Forum 2016 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Neural computing & applications - Springer London, 1993, 30(2016), 7 vom: 31. Dez., Seite 2295-2304 |
|---|---|
| Übergeordnetes Werk: |
volume:30 ; year:2016 ; number:7 ; day:31 ; month:12 ; pages:2295-2304 |
| Links: |
|---|
| DOI / URN: |
10.1007/s00521-016-2783-9 |
|---|
| Katalog-ID: |
OLC2025607784 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | OLC2025607784 | ||
| 003 | DE-627 | ||
| 005 | 20230502114755.0 | ||
| 007 | tu | ||
| 008 | 200820s2016 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s00521-016-2783-9 |2 doi | |
| 035 | |a (DE-627)OLC2025607784 | ||
| 035 | |a (DE-He213)s00521-016-2783-9-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 Yin, Zihong |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a A-optimal convolutional neural network |
| 264 | 1 | |c 2016 | |
| 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 Natural Computing Applications Forum 2016 | ||
| 520 | |a Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model. | ||
| 650 | 4 | |a A-optimality | |
| 650 | 4 | |a Convolutional neural network | |
| 650 | 4 | |a Alternate optimization | |
| 650 | 4 | |a Gradient descent | |
| 650 | 4 | |a Seismic waveform | |
| 700 | 1 | |a Kong, Dehui |4 aut | |
| 700 | 1 | |a Shao, Guoxia |4 aut | |
| 700 | 1 | |a Ning, Xinran |4 aut | |
| 700 | 1 | |a Jin, Warren |4 aut | |
| 700 | 1 | |a Wang, Jing-Yan |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Neural computing & applications |d Springer London, 1993 |g 30(2016), 7 vom: 31. Dez., Seite 2295-2304 |w (DE-627)165669608 |w (DE-600)1136944-9 |w (DE-576)032873050 |x 0941-0643 |7 nnns |
| 773 | 1 | 8 | |g volume:30 |g year:2016 |g number:7 |g day:31 |g month:12 |g pages:2295-2304 |
| 856 | 4 | 1 | |u https://doi.org/10.1007/s00521-016-2783-9 |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_70 | ||
| 912 | |a GBV_ILN_2018 | ||
| 912 | |a GBV_ILN_4046 | ||
| 912 | |a GBV_ILN_4277 | ||
| 951 | |a AR | ||
| 952 | |d 30 |j 2016 |e 7 |b 31 |c 12 |h 2295-2304 | ||
| author_variant |
z y zy d k dk g s gs x n xn w j wj j y w jyw |
|---|---|
| matchkey_str |
article:09410643:2016----::otmlovltoanu |
| hierarchy_sort_str |
2016 |
| publishDate |
2016 |
| allfields |
10.1007/s00521-016-2783-9 doi (DE-627)OLC2025607784 (DE-He213)s00521-016-2783-9-p DE-627 ger DE-627 rakwb eng 004 VZ Yin, Zihong verfasserin aut A-optimal convolutional neural network 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Natural Computing Applications Forum 2016 Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model. A-optimality Convolutional neural network Alternate optimization Gradient descent Seismic waveform Kong, Dehui aut Shao, Guoxia aut Ning, Xinran aut Jin, Warren aut Wang, Jing-Yan aut Enthalten in Neural computing & applications Springer London, 1993 30(2016), 7 vom: 31. Dez., Seite 2295-2304 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:30 year:2016 number:7 day:31 month:12 pages:2295-2304 https://doi.org/10.1007/s00521-016-2783-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4046 GBV_ILN_4277 AR 30 2016 7 31 12 2295-2304 |
| spelling |
10.1007/s00521-016-2783-9 doi (DE-627)OLC2025607784 (DE-He213)s00521-016-2783-9-p DE-627 ger DE-627 rakwb eng 004 VZ Yin, Zihong verfasserin aut A-optimal convolutional neural network 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Natural Computing Applications Forum 2016 Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model. A-optimality Convolutional neural network Alternate optimization Gradient descent Seismic waveform Kong, Dehui aut Shao, Guoxia aut Ning, Xinran aut Jin, Warren aut Wang, Jing-Yan aut Enthalten in Neural computing & applications Springer London, 1993 30(2016), 7 vom: 31. Dez., Seite 2295-2304 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:30 year:2016 number:7 day:31 month:12 pages:2295-2304 https://doi.org/10.1007/s00521-016-2783-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4046 GBV_ILN_4277 AR 30 2016 7 31 12 2295-2304 |
| allfields_unstemmed |
10.1007/s00521-016-2783-9 doi (DE-627)OLC2025607784 (DE-He213)s00521-016-2783-9-p DE-627 ger DE-627 rakwb eng 004 VZ Yin, Zihong verfasserin aut A-optimal convolutional neural network 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Natural Computing Applications Forum 2016 Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model. A-optimality Convolutional neural network Alternate optimization Gradient descent Seismic waveform Kong, Dehui aut Shao, Guoxia aut Ning, Xinran aut Jin, Warren aut Wang, Jing-Yan aut Enthalten in Neural computing & applications Springer London, 1993 30(2016), 7 vom: 31. Dez., Seite 2295-2304 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:30 year:2016 number:7 day:31 month:12 pages:2295-2304 https://doi.org/10.1007/s00521-016-2783-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4046 GBV_ILN_4277 AR 30 2016 7 31 12 2295-2304 |
| allfieldsGer |
10.1007/s00521-016-2783-9 doi (DE-627)OLC2025607784 (DE-He213)s00521-016-2783-9-p DE-627 ger DE-627 rakwb eng 004 VZ Yin, Zihong verfasserin aut A-optimal convolutional neural network 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Natural Computing Applications Forum 2016 Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model. A-optimality Convolutional neural network Alternate optimization Gradient descent Seismic waveform Kong, Dehui aut Shao, Guoxia aut Ning, Xinran aut Jin, Warren aut Wang, Jing-Yan aut Enthalten in Neural computing & applications Springer London, 1993 30(2016), 7 vom: 31. Dez., Seite 2295-2304 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:30 year:2016 number:7 day:31 month:12 pages:2295-2304 https://doi.org/10.1007/s00521-016-2783-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4046 GBV_ILN_4277 AR 30 2016 7 31 12 2295-2304 |
| allfieldsSound |
10.1007/s00521-016-2783-9 doi (DE-627)OLC2025607784 (DE-He213)s00521-016-2783-9-p DE-627 ger DE-627 rakwb eng 004 VZ Yin, Zihong verfasserin aut A-optimal convolutional neural network 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © The Natural Computing Applications Forum 2016 Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model. A-optimality Convolutional neural network Alternate optimization Gradient descent Seismic waveform Kong, Dehui aut Shao, Guoxia aut Ning, Xinran aut Jin, Warren aut Wang, Jing-Yan aut Enthalten in Neural computing & applications Springer London, 1993 30(2016), 7 vom: 31. Dez., Seite 2295-2304 (DE-627)165669608 (DE-600)1136944-9 (DE-576)032873050 0941-0643 nnns volume:30 year:2016 number:7 day:31 month:12 pages:2295-2304 https://doi.org/10.1007/s00521-016-2783-9 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4046 GBV_ILN_4277 AR 30 2016 7 31 12 2295-2304 |
| language |
English |
| source |
Enthalten in Neural computing & applications 30(2016), 7 vom: 31. Dez., Seite 2295-2304 volume:30 year:2016 number:7 day:31 month:12 pages:2295-2304 |
| sourceStr |
Enthalten in Neural computing & applications 30(2016), 7 vom: 31. Dez., Seite 2295-2304 volume:30 year:2016 number:7 day:31 month:12 pages:2295-2304 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
A-optimality Convolutional neural network Alternate optimization Gradient descent Seismic waveform |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
Neural computing & applications |
| authorswithroles_txt_mv |
Yin, Zihong @@aut@@ Kong, Dehui @@aut@@ Shao, Guoxia @@aut@@ Ning, Xinran @@aut@@ Jin, Warren @@aut@@ Wang, Jing-Yan @@aut@@ |
| publishDateDaySort_date |
2016-12-31T00:00:00Z |
| hierarchy_top_id |
165669608 |
| dewey-sort |
14 |
| id |
OLC2025607784 |
| 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">OLC2025607784</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230502114755.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200820s2016 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00521-016-2783-9</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2025607784</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00521-016-2783-9-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">Yin, Zihong</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">A-optimal convolutional neural network</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016</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 Natural Computing Applications Forum 2016</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">A-optimality</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Convolutional neural network</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Alternate optimization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Gradient descent</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Seismic waveform</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kong, Dehui</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shao, Guoxia</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ning, Xinran</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Jin, Warren</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Jing-Yan</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">30(2016), 7 vom: 31. Dez., Seite 2295-2304</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:30</subfield><subfield code="g">year:2016</subfield><subfield code="g">number:7</subfield><subfield code="g">day:31</subfield><subfield code="g">month:12</subfield><subfield code="g">pages:2295-2304</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00521-016-2783-9</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_70</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_4046</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">30</subfield><subfield code="j">2016</subfield><subfield code="e">7</subfield><subfield code="b">31</subfield><subfield code="c">12</subfield><subfield code="h">2295-2304</subfield></datafield></record></collection>
|
| author |
Yin, Zihong |
| spellingShingle |
Yin, Zihong ddc 004 misc A-optimality misc Convolutional neural network misc Alternate optimization misc Gradient descent misc Seismic waveform A-optimal convolutional neural network |
| authorStr |
Yin, Zihong |
| 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 aut aut aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0941-0643 |
| topic_title |
004 VZ A-optimal convolutional neural network A-optimality Convolutional neural network Alternate optimization Gradient descent Seismic waveform |
| topic |
ddc 004 misc A-optimality misc Convolutional neural network misc Alternate optimization misc Gradient descent misc Seismic waveform |
| topic_unstemmed |
ddc 004 misc A-optimality misc Convolutional neural network misc Alternate optimization misc Gradient descent misc Seismic waveform |
| topic_browse |
ddc 004 misc A-optimality misc Convolutional neural network misc Alternate optimization misc Gradient descent misc Seismic waveform |
| 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 |
A-optimal convolutional neural network |
| ctrlnum |
(DE-627)OLC2025607784 (DE-He213)s00521-016-2783-9-p |
| title_full |
A-optimal convolutional neural network |
| author_sort |
Yin, Zihong |
| 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 |
2016 |
| contenttype_str_mv |
txt |
| container_start_page |
2295 |
| author_browse |
Yin, Zihong Kong, Dehui Shao, Guoxia Ning, Xinran Jin, Warren Wang, Jing-Yan |
| container_volume |
30 |
| class |
004 VZ |
| format_se |
Aufsätze |
| author-letter |
Yin, Zihong |
| doi_str_mv |
10.1007/s00521-016-2783-9 |
| dewey-full |
004 |
| title_sort |
a-optimal convolutional neural network |
| title_auth |
A-optimal convolutional neural network |
| abstract |
Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model. © The Natural Computing Applications Forum 2016 |
| abstractGer |
Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model. © The Natural Computing Applications Forum 2016 |
| abstract_unstemmed |
Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model. © The Natural Computing Applications Forum 2016 |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_70 GBV_ILN_2018 GBV_ILN_4046 GBV_ILN_4277 |
| container_issue |
7 |
| title_short |
A-optimal convolutional neural network |
| url |
https://doi.org/10.1007/s00521-016-2783-9 |
| remote_bool |
false |
| author2 |
Kong, Dehui Shao, Guoxia Ning, Xinran Jin, Warren Wang, Jing-Yan |
| author2Str |
Kong, Dehui Shao, Guoxia Ning, Xinran Jin, Warren Wang, Jing-Yan |
| ppnlink |
165669608 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| doi_str |
10.1007/s00521-016-2783-9 |
| up_date |
2024-07-04T01:41:26.409Z |
| _version_ |
1803610789164089345 |
| 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">OLC2025607784</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230502114755.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200820s2016 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s00521-016-2783-9</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2025607784</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s00521-016-2783-9-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">Yin, Zihong</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">A-optimal convolutional neural network</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016</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 Natural Computing Applications Forum 2016</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract In this paper, we propose a novel data representation-classification model learning algorithm. The model is a convolutional neural network (CNN), and we learn its parameters to achieve A-optimality. The input multi-instance data are represented by a CNN model, and then classified by a linear classification model. The A-optimality of a classification model is measured by the trace of the covariance matrix of the model parameter vector. To achieve the A-optimality of the CNN model, we minimize the classification errors and a regularization term to present the classification model parameter as a function of the CNN filter parameters, and minimize its trace of the covariance matrix. We show that the minimization problem can be solved easily by transferring it to another coupled minimization problem. In the experiments over benchmark data sets of molecular, image, and seismic waveform, we show the advantages of the proposed A-optimal CNN model.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">A-optimality</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Convolutional neural network</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Alternate optimization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Gradient descent</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Seismic waveform</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kong, Dehui</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shao, Guoxia</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Ning, Xinran</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Jin, Warren</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Wang, Jing-Yan</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">30(2016), 7 vom: 31. Dez., Seite 2295-2304</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:30</subfield><subfield code="g">year:2016</subfield><subfield code="g">number:7</subfield><subfield code="g">day:31</subfield><subfield code="g">month:12</subfield><subfield code="g">pages:2295-2304</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s00521-016-2783-9</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_70</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_4046</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">30</subfield><subfield code="j">2016</subfield><subfield code="e">7</subfield><subfield code="b">31</subfield><subfield code="c">12</subfield><subfield code="h">2295-2304</subfield></datafield></record></collection>
|
| score |
7.4021244 |