Modular neural network via exploring category hierarchy
Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function....
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Han, Wei [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2021transfer abstract |
|---|
| Schlagwörter: |
|---|
| Umfang: |
12 |
|---|
| Übergeordnetes Werk: |
Enthalten in: Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study - Petrruzziello, Carmelina ELSEVIER, 2013, an international journal, New York, NY |
|---|---|
| Übergeordnetes Werk: |
volume:569 ; year:2021 ; pages:496-507 ; extent:12 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.ins.2021.05.032 |
|---|
| Katalog-ID: |
ELV054347130 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV054347130 | ||
| 003 | DE-627 | ||
| 005 | 20230626040017.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 210910s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.ins.2021.05.032 |2 doi | |
| 028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001418.pica |
| 035 | |a (DE-627)ELV054347130 | ||
| 035 | |a (ELSEVIER)S0020-0255(21)00490-4 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 610 |q VZ |
| 082 | 0 | 4 | |a 570 |q VZ |
| 084 | |a BIODIV |q DE-30 |2 fid | ||
| 084 | |a 35.70 |2 bkl | ||
| 084 | |a 42.12 |2 bkl | ||
| 084 | |a 42.15 |2 bkl | ||
| 100 | 1 | |a Han, Wei |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Modular neural network via exploring category hierarchy |
| 264 | 1 | |c 2021transfer abstract | |
| 300 | |a 12 | ||
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. | ||
| 520 | |a Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. | ||
| 650 | 7 | |a 62H30 |2 Elsevier | |
| 650 | 7 | |a 68T07 |2 Elsevier | |
| 700 | 1 | |a Zheng, Changgang |4 oth | |
| 700 | 1 | |a Zhang, Rui |4 oth | |
| 700 | 1 | |a Guo, Jinxia |4 oth | |
| 700 | 1 | |a Yang, Qinli |4 oth | |
| 700 | 1 | |a Shao, Junming |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier Science Inc |a Petrruzziello, Carmelina ELSEVIER |t Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study |d 2013 |d an international journal |g New York, NY |w (DE-627)ELV011843691 |
| 773 | 1 | 8 | |g volume:569 |g year:2021 |g pages:496-507 |g extent:12 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.ins.2021.05.032 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a FID-BIODIV | ||
| 912 | |a SSG-OLC-PHA | ||
| 936 | b | k | |a 35.70 |j Biochemie: Allgemeines |q VZ |
| 936 | b | k | |a 42.12 |j Biophysik |q VZ |
| 936 | b | k | |a 42.15 |j Zellbiologie |q VZ |
| 951 | |a AR | ||
| 952 | |d 569 |j 2021 |h 496-507 |g 12 | ||
| author_variant |
w h wh |
|---|---|
| matchkey_str |
hanweizhengchanggangzhangruiguojinxiayan:2021----:ouanuantokiepoigae |
| hierarchy_sort_str |
2021transfer abstract |
| bklnumber |
35.70 42.12 42.15 |
| publishDate |
2021 |
| allfields |
10.1016/j.ins.2021.05.032 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001418.pica (DE-627)ELV054347130 (ELSEVIER)S0020-0255(21)00490-4 DE-627 ger DE-627 rakwb eng 610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Han, Wei verfasserin aut Modular neural network via exploring category hierarchy 2021transfer abstract 12 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. 62H30 Elsevier 68T07 Elsevier Zheng, Changgang oth Zhang, Rui oth Guo, Jinxia oth Yang, Qinli oth Shao, Junming oth Enthalten in Elsevier Science Inc Petrruzziello, Carmelina ELSEVIER Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study 2013 an international journal New York, NY (DE-627)ELV011843691 volume:569 year:2021 pages:496-507 extent:12 https://doi.org/10.1016/j.ins.2021.05.032 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA 35.70 Biochemie: Allgemeines VZ 42.12 Biophysik VZ 42.15 Zellbiologie VZ AR 569 2021 496-507 12 |
| spelling |
10.1016/j.ins.2021.05.032 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001418.pica (DE-627)ELV054347130 (ELSEVIER)S0020-0255(21)00490-4 DE-627 ger DE-627 rakwb eng 610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Han, Wei verfasserin aut Modular neural network via exploring category hierarchy 2021transfer abstract 12 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. 62H30 Elsevier 68T07 Elsevier Zheng, Changgang oth Zhang, Rui oth Guo, Jinxia oth Yang, Qinli oth Shao, Junming oth Enthalten in Elsevier Science Inc Petrruzziello, Carmelina ELSEVIER Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study 2013 an international journal New York, NY (DE-627)ELV011843691 volume:569 year:2021 pages:496-507 extent:12 https://doi.org/10.1016/j.ins.2021.05.032 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA 35.70 Biochemie: Allgemeines VZ 42.12 Biophysik VZ 42.15 Zellbiologie VZ AR 569 2021 496-507 12 |
| allfields_unstemmed |
10.1016/j.ins.2021.05.032 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001418.pica (DE-627)ELV054347130 (ELSEVIER)S0020-0255(21)00490-4 DE-627 ger DE-627 rakwb eng 610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Han, Wei verfasserin aut Modular neural network via exploring category hierarchy 2021transfer abstract 12 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. 62H30 Elsevier 68T07 Elsevier Zheng, Changgang oth Zhang, Rui oth Guo, Jinxia oth Yang, Qinli oth Shao, Junming oth Enthalten in Elsevier Science Inc Petrruzziello, Carmelina ELSEVIER Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study 2013 an international journal New York, NY (DE-627)ELV011843691 volume:569 year:2021 pages:496-507 extent:12 https://doi.org/10.1016/j.ins.2021.05.032 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA 35.70 Biochemie: Allgemeines VZ 42.12 Biophysik VZ 42.15 Zellbiologie VZ AR 569 2021 496-507 12 |
| allfieldsGer |
10.1016/j.ins.2021.05.032 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001418.pica (DE-627)ELV054347130 (ELSEVIER)S0020-0255(21)00490-4 DE-627 ger DE-627 rakwb eng 610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Han, Wei verfasserin aut Modular neural network via exploring category hierarchy 2021transfer abstract 12 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. 62H30 Elsevier 68T07 Elsevier Zheng, Changgang oth Zhang, Rui oth Guo, Jinxia oth Yang, Qinli oth Shao, Junming oth Enthalten in Elsevier Science Inc Petrruzziello, Carmelina ELSEVIER Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study 2013 an international journal New York, NY (DE-627)ELV011843691 volume:569 year:2021 pages:496-507 extent:12 https://doi.org/10.1016/j.ins.2021.05.032 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA 35.70 Biochemie: Allgemeines VZ 42.12 Biophysik VZ 42.15 Zellbiologie VZ AR 569 2021 496-507 12 |
| allfieldsSound |
10.1016/j.ins.2021.05.032 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001418.pica (DE-627)ELV054347130 (ELSEVIER)S0020-0255(21)00490-4 DE-627 ger DE-627 rakwb eng 610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Han, Wei verfasserin aut Modular neural network via exploring category hierarchy 2021transfer abstract 12 nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. 62H30 Elsevier 68T07 Elsevier Zheng, Changgang oth Zhang, Rui oth Guo, Jinxia oth Yang, Qinli oth Shao, Junming oth Enthalten in Elsevier Science Inc Petrruzziello, Carmelina ELSEVIER Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study 2013 an international journal New York, NY (DE-627)ELV011843691 volume:569 year:2021 pages:496-507 extent:12 https://doi.org/10.1016/j.ins.2021.05.032 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA 35.70 Biochemie: Allgemeines VZ 42.12 Biophysik VZ 42.15 Zellbiologie VZ AR 569 2021 496-507 12 |
| language |
English |
| source |
Enthalten in Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study New York, NY volume:569 year:2021 pages:496-507 extent:12 |
| sourceStr |
Enthalten in Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study New York, NY volume:569 year:2021 pages:496-507 extent:12 |
| format_phy_str_mv |
Article |
| bklname |
Biochemie: Allgemeines Biophysik Zellbiologie |
| institution |
findex.gbv.de |
| topic_facet |
62H30 68T07 |
| dewey-raw |
610 |
| isfreeaccess_bool |
false |
| container_title |
Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study |
| authorswithroles_txt_mv |
Han, Wei @@aut@@ Zheng, Changgang @@oth@@ Zhang, Rui @@oth@@ Guo, Jinxia @@oth@@ Yang, Qinli @@oth@@ Shao, Junming @@oth@@ |
| publishDateDaySort_date |
2021-01-01T00:00:00Z |
| hierarchy_top_id |
ELV011843691 |
| dewey-sort |
3610 |
| id |
ELV054347130 |
| 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">ELV054347130</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626040017.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.ins.2021.05.032</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001418.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV054347130</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0020-0255(21)00490-4</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">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">570</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">BIODIV</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">35.70</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.12</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.15</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Han, Wei</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Modular neural network via exploring category hierarchy</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">12</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">62H30</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">68T07</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zheng, Changgang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Rui</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Guo, Jinxia</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yang, Qinli</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shao, Junming</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science Inc</subfield><subfield code="a">Petrruzziello, Carmelina ELSEVIER</subfield><subfield code="t">Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study</subfield><subfield code="d">2013</subfield><subfield code="d">an international journal</subfield><subfield code="g">New York, NY</subfield><subfield code="w">(DE-627)ELV011843691</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:569</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:496-507</subfield><subfield code="g">extent:12</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.ins.2021.05.032</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-BIODIV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">35.70</subfield><subfield code="j">Biochemie: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.12</subfield><subfield code="j">Biophysik</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.15</subfield><subfield code="j">Zellbiologie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">569</subfield><subfield code="j">2021</subfield><subfield code="h">496-507</subfield><subfield code="g">12</subfield></datafield></record></collection>
|
| author |
Han, Wei |
| spellingShingle |
Han, Wei ddc 610 ddc 570 fid BIODIV bkl 35.70 bkl 42.12 bkl 42.15 Elsevier 62H30 Elsevier 68T07 Modular neural network via exploring category hierarchy |
| authorStr |
Han, Wei |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV011843691 |
| format |
electronic Article |
| dewey-ones |
610 - Medicine & health 570 - Life sciences; biology |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl Modular neural network via exploring category hierarchy 62H30 Elsevier 68T07 Elsevier |
| topic |
ddc 610 ddc 570 fid BIODIV bkl 35.70 bkl 42.12 bkl 42.15 Elsevier 62H30 Elsevier 68T07 |
| topic_unstemmed |
ddc 610 ddc 570 fid BIODIV bkl 35.70 bkl 42.12 bkl 42.15 Elsevier 62H30 Elsevier 68T07 |
| topic_browse |
ddc 610 ddc 570 fid BIODIV bkl 35.70 bkl 42.12 bkl 42.15 Elsevier 62H30 Elsevier 68T07 |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
c z cz r z rz j g jg q y qy j s js |
| hierarchy_parent_title |
Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study |
| hierarchy_parent_id |
ELV011843691 |
| dewey-tens |
610 - Medicine & health 570 - Life sciences; biology |
| hierarchy_top_title |
Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV011843691 |
| title |
Modular neural network via exploring category hierarchy |
| ctrlnum |
(DE-627)ELV054347130 (ELSEVIER)S0020-0255(21)00490-4 |
| title_full |
Modular neural network via exploring category hierarchy |
| author_sort |
Han, Wei |
| journal |
Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study |
| journalStr |
Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology 500 - Science |
| recordtype |
marc |
| publishDateSort |
2021 |
| contenttype_str_mv |
zzz |
| container_start_page |
496 |
| author_browse |
Han, Wei |
| container_volume |
569 |
| physical |
12 |
| class |
610 VZ 570 VZ BIODIV DE-30 fid 35.70 bkl 42.12 bkl 42.15 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Han, Wei |
| doi_str_mv |
10.1016/j.ins.2021.05.032 |
| dewey-full |
610 570 |
| title_sort |
modular neural network via exploring category hierarchy |
| title_auth |
Modular neural network via exploring category hierarchy |
| abstract |
Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. |
| abstractGer |
Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. |
| abstract_unstemmed |
Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U FID-BIODIV SSG-OLC-PHA |
| title_short |
Modular neural network via exploring category hierarchy |
| url |
https://doi.org/10.1016/j.ins.2021.05.032 |
| remote_bool |
true |
| author2 |
Zheng, Changgang Zhang, Rui Guo, Jinxia Yang, Qinli Shao, Junming |
| author2Str |
Zheng, Changgang Zhang, Rui Guo, Jinxia Yang, Qinli Shao, Junming |
| ppnlink |
ELV011843691 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth oth oth |
| doi_str |
10.1016/j.ins.2021.05.032 |
| up_date |
2024-07-06T21:28:38.487Z |
| _version_ |
1803866675335921664 |
| 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">ELV054347130</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626040017.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">210910s2021 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.ins.2021.05.032</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001418.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV054347130</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0020-0255(21)00490-4</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">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">570</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">BIODIV</subfield><subfield code="q">DE-30</subfield><subfield code="2">fid</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">35.70</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.12</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">42.15</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Han, Wei</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Modular neural network via exploring category hierarchy</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2021transfer abstract</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">12</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Modular is a powerful and inherently hierarchical concept in the human brain to process a large variety of complex tasks. Converging evidence has shown several advantages to hierarchically modular network organizations in the human brain such as interpretability and evolvability of network function. Inspired by previous neuroscience studies, we propose MNN-CH, a novel modular neural network that is constructed with explored category hierarchy. The basic idea is learning to learn an optimized category hierarchy to decompose complex patterns. And specific patterns are imposed into corresponding modules to realize a transparent design of the neural network. Specifically, for a given classification task, each class or superclass is first represented as a prototype. Afterward, the category hierarchy is initially determined by investigating class similarity and gather similar ones to train each branch neural network (i.e., modular) separately. Finally, an error-driven prototype learning is introduced to refine the category hierarchy by updating the class-superclass affiliation. Experiment results on several image classification datasets show that our model has a good performance, especially in complex tasks. Beyond, we conduct an analysis to illustrate the tree-manner interpretability of the modular neural network.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">62H30</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">68T07</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zheng, Changgang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Zhang, Rui</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Guo, Jinxia</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Yang, Qinli</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Shao, Junming</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier Science Inc</subfield><subfield code="a">Petrruzziello, Carmelina ELSEVIER</subfield><subfield code="t">Mo1264 Clinical Characteristics of Inflammatory Bowel Disease May Influence the Cancer Risk When Using Immunomodulators: Incident Cases of Cancer in a Multicenter Case-Control Study</subfield><subfield code="d">2013</subfield><subfield code="d">an international journal</subfield><subfield code="g">New York, NY</subfield><subfield code="w">(DE-627)ELV011843691</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:569</subfield><subfield code="g">year:2021</subfield><subfield code="g">pages:496-507</subfield><subfield code="g">extent:12</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.ins.2021.05.032</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">FID-BIODIV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">35.70</subfield><subfield code="j">Biochemie: Allgemeines</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.12</subfield><subfield code="j">Biophysik</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">42.15</subfield><subfield code="j">Zellbiologie</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">569</subfield><subfield code="j">2021</subfield><subfield code="h">496-507</subfield><subfield code="g">12</subfield></datafield></record></collection>
|
| score |
7.4011774 |