Learning with recurrent neural networks:
Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a...
Saved in:
| Main Author: | |
|---|---|
| Format: | Electronic eBook |
| Language: | English |
| Published: |
London
Springer London
2000
|
| Series: | Lecture Notes in Control and Information Sciences
254 |
| Subjects: | |
| Online Access: | BTU01 FHI01 Volltext |
| Summary: | Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated- including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes. Finally, the complexity of training is considered - including new results on the loading problem for standard feedforward networks with an arbitrary multilayered architecture, a correlated number of neurons and training set size, a varying number of hidden neurons but fixed input dimension, or the sigmoidal activation function, respectively |
| Physical Description: | 1 Online-Ressource (150 p) |
| ISBN: | 9781846285677 |
| DOI: | 10.1007/BFb0110016 |
Staff View
MARC
| LEADER | 00000nmm a2200000zcb4500 | ||
|---|---|---|---|
| 001 | BV045149088 | ||
| 003 | DE-604 | ||
| 005 | 20190425 | ||
| 007 | cr|uuu---uuuuu | ||
| 008 | 180827s2000 |||| o||u| ||||||eng d | ||
| 020 | |a 9781846285677 |9 978-1-84628-567-7 | ||
| 024 | 7 | |a 10.1007/BFb0110016 |2 doi | |
| 035 | |a (ZDB-2-ENG)978-1-84628-567-7 | ||
| 035 | |a (OCoLC)849892845 | ||
| 035 | |a (DE-599)BVBBV045149088 | ||
| 040 | |a DE-604 |b ger |e aacr | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-573 |a DE-634 | ||
| 082 | 0 | |a 629.8 |2 23 | |
| 084 | |a SI 845 |0 (DE-625)143198: |2 rvk | ||
| 100 | 1 | |a Hammer, Barbara |d 1970- |e Verfasser |0 (DE-588)13377435X |4 aut | |
| 245 | 1 | 0 | |a Learning with recurrent neural networks |c by Barbara Hammer |
| 264 | 1 | |a London |b Springer London |c 2000 | |
| 300 | |a 1 Online-Ressource (150 p) | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b c |2 rdamedia | ||
| 338 | |b cr |2 rdacarrier | ||
| 490 | 0 | |a Lecture Notes in Control and Information Sciences |v 254 | |
| 520 | |a Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated- including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes. Finally, the complexity of training is considered - including new results on the loading problem for standard feedforward networks with an arbitrary multilayered architecture, a correlated number of neurons and training set size, a varying number of hidden neurons but fixed input dimension, or the sigmoidal activation function, respectively | ||
| 650 | 4 | |a Engineering | |
| 650 | 4 | |a Control, Robotics, Mechatronics | |
| 650 | 4 | |a Engineering | |
| 650 | 4 | |a Control engineering | |
| 650 | 4 | |a Robotics | |
| 650 | 4 | |a Mechatronics | |
| 650 | 0 | 7 | |a Rekursives neuronales Netz |0 (DE-588)4379549-3 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Neuronales Netz |0 (DE-588)4226127-2 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a NP-vollständiges Problem |0 (DE-588)4138229-8 |2 gnd |9 rswk-swf |
| 655 | 7 | |8 1\p |0 (DE-588)4113937-9 |a Hochschulschrift |2 gnd-content | |
| 689 | 0 | 0 | |a Rekursives neuronales Netz |0 (DE-588)4379549-3 |D s |
| 689 | 0 | 1 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 0 | 2 | |a NP-vollständiges Problem |0 (DE-588)4138229-8 |D s |
| 689 | 0 | |8 2\p |5 DE-604 | |
| 689 | 1 | 0 | |a Maschinelles Lernen |0 (DE-588)4193754-5 |D s |
| 689 | 1 | 1 | |a Neuronales Netz |0 (DE-588)4226127-2 |D s |
| 689 | 1 | |8 3\p |5 DE-604 | |
| 776 | 0 | 8 | |i Erscheint auch als |n Druck-Ausgabe |z 9781852333430 |
| 856 | 4 | 0 | |u https://doi.org/10.1007/BFb0110016 |x Verlag |z URL des Erstveröffentlichers |3 Volltext |
| 912 | |a ZDB-2-ENG | ||
| 940 | 1 | |q ZDB-2-ENG_2000/2004 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-030538787 | ||
| 883 | 1 | |8 1\p |a cgwrk |d 20201028 |q DE-101 |u https://d-nb.info/provenance/plan#cgwrk | |
| 883 | 1 | |8 2\p |a cgwrk |d 20201028 |q DE-101 |u https://d-nb.info/provenance/plan#cgwrk | |
| 883 | 1 | |8 3\p |a cgwrk |d 20201028 |q DE-101 |u https://d-nb.info/provenance/plan#cgwrk | |
| 966 | e | |u https://doi.org/10.1007/BFb0110016 |l BTU01 |p ZDB-2-ENG |q ZDB-2-ENG_Archiv |x Verlag |3 Volltext | |
| 966 | e | |u https://doi.org/10.1007/BFb0110016 |l FHI01 |p ZDB-2-ENG |q ZDB-2-ENG_2000/2004 |x Verlag |3 Volltext | |
Record in the Search Index
| _version_ | 1804178820199088128 |
|---|---|
| any_adam_object | |
| author | Hammer, Barbara 1970- |
| author_GND | (DE-588)13377435X |
| author_facet | Hammer, Barbara 1970- |
| author_role | aut |
| author_sort | Hammer, Barbara 1970- |
| author_variant | b h bh |
| building | Verbundindex |
| bvnumber | BV045149088 |
| classification_rvk | SI 845 |
| collection | ZDB-2-ENG |
| ctrlnum | (ZDB-2-ENG)978-1-84628-567-7 (OCoLC)849892845 (DE-599)BVBBV045149088 |
| dewey-full | 629.8 |
| dewey-hundreds | 600 - Technology (Applied sciences) |
| dewey-ones | 629 - Other branches of engineering |
| dewey-raw | 629.8 |
| dewey-search | 629.8 |
| dewey-sort | 3629.8 |
| dewey-tens | 620 - Engineering and allied operations |
| discipline | Mathematik Mess-/Steuerungs-/Regelungs-/Automatisierungstechnik / Mechatronik |
| doi_str_mv | 10.1007/BFb0110016 |
| format | Electronic eBook |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>03875nmm a2200649zcb4500</leader><controlfield tag="001">BV045149088</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">20190425 </controlfield><controlfield tag="007">cr|uuu---uuuuu</controlfield><controlfield tag="008">180827s2000 |||| o||u| ||||||eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9781846285677</subfield><subfield code="9">978-1-84628-567-7</subfield></datafield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/BFb0110016</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ZDB-2-ENG)978-1-84628-567-7</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)849892845</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV045149088</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">aacr</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-573</subfield><subfield code="a">DE-634</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">629.8</subfield><subfield code="2">23</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">SI 845</subfield><subfield code="0">(DE-625)143198:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Hammer, Barbara</subfield><subfield code="d">1970-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)13377435X</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Learning with recurrent neural networks</subfield><subfield code="c">by Barbara Hammer</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">London</subfield><subfield code="b">Springer London</subfield><subfield code="c">2000</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 Online-Ressource (150 p)</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="0" ind2=" "><subfield code="a">Lecture Notes in Control and Information Sciences</subfield><subfield code="v">254</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated- including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes. Finally, the complexity of training is considered - including new results on the loading problem for standard feedforward networks with an arbitrary multilayered architecture, a correlated number of neurons and training set size, a varying number of hidden neurons but fixed input dimension, or the sigmoidal activation function, respectively</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Engineering</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Control, Robotics, Mechatronics</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Engineering</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Control engineering</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Robotics</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Mechatronics</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Rekursives neuronales Netz</subfield><subfield code="0">(DE-588)4379549-3</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Neuronales Netz</subfield><subfield code="0">(DE-588)4226127-2</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">NP-vollständiges Problem</subfield><subfield code="0">(DE-588)4138229-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="655" ind1=" " ind2="7"><subfield code="8">1\p</subfield><subfield code="0">(DE-588)4113937-9</subfield><subfield code="a">Hochschulschrift</subfield><subfield code="2">gnd-content</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Rekursives neuronales Netz</subfield><subfield code="0">(DE-588)4379549-3</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="2"><subfield code="a">NP-vollständiges Problem</subfield><subfield code="0">(DE-588)4138229-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="8">2\p</subfield><subfield code="5">DE-604</subfield></datafield><datafield tag="689" ind1="1" ind2="0"><subfield code="a">Maschinelles Lernen</subfield><subfield code="0">(DE-588)4193754-5</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2="1"><subfield code="a">Neuronales Netz</subfield><subfield code="0">(DE-588)4226127-2</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="1" ind2=" "><subfield code="8">3\p</subfield><subfield code="5">DE-604</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Druck-Ausgabe</subfield><subfield code="z">9781852333430</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1007/BFb0110016</subfield><subfield code="x">Verlag</subfield><subfield code="z">URL des Erstveröffentlichers</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-2-ENG</subfield></datafield><datafield tag="940" ind1="1" ind2=" "><subfield code="q">ZDB-2-ENG_2000/2004</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-030538787</subfield></datafield><datafield tag="883" ind1="1" ind2=" "><subfield code="8">1\p</subfield><subfield code="a">cgwrk</subfield><subfield code="d">20201028</subfield><subfield code="q">DE-101</subfield><subfield code="u">https://d-nb.info/provenance/plan#cgwrk</subfield></datafield><datafield tag="883" ind1="1" ind2=" "><subfield code="8">2\p</subfield><subfield code="a">cgwrk</subfield><subfield code="d">20201028</subfield><subfield code="q">DE-101</subfield><subfield code="u">https://d-nb.info/provenance/plan#cgwrk</subfield></datafield><datafield tag="883" ind1="1" ind2=" "><subfield code="8">3\p</subfield><subfield code="a">cgwrk</subfield><subfield code="d">20201028</subfield><subfield code="q">DE-101</subfield><subfield code="u">https://d-nb.info/provenance/plan#cgwrk</subfield></datafield><datafield tag="966" ind1="e" ind2=" "><subfield code="u">https://doi.org/10.1007/BFb0110016</subfield><subfield code="l">BTU01</subfield><subfield code="p">ZDB-2-ENG</subfield><subfield code="q">ZDB-2-ENG_Archiv</subfield><subfield code="x">Verlag</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="966" ind1="e" ind2=" "><subfield code="u">https://doi.org/10.1007/BFb0110016</subfield><subfield code="l">FHI01</subfield><subfield code="p">ZDB-2-ENG</subfield><subfield code="q">ZDB-2-ENG_2000/2004</subfield><subfield code="x">Verlag</subfield><subfield code="3">Volltext</subfield></datafield></record></collection> |
| genre | 1\p (DE-588)4113937-9 Hochschulschrift gnd-content |
| genre_facet | Hochschulschrift |
| id | DE-604.BV045149088 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-10T08:10:02Z |
| institution | BVB |
| isbn | 9781846285677 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-030538787 |
| oclc_num | 849892845 |
| open_access_boolean | |
| owner | DE-573 DE-634 |
| owner_facet | DE-573 DE-634 |
| physical | 1 Online-Ressource (150 p) |
| psigel | ZDB-2-ENG ZDB-2-ENG_2000/2004 ZDB-2-ENG ZDB-2-ENG_Archiv ZDB-2-ENG ZDB-2-ENG_2000/2004 |
| publishDate | 2000 |
| publishDateSearch | 2000 |
| publishDateSort | 2000 |
| publisher | Springer London |
| record_format | marc |
| series2 | Lecture Notes in Control and Information Sciences |
| spelling | Hammer, Barbara 1970- Verfasser (DE-588)13377435X aut Learning with recurrent neural networks by Barbara Hammer London Springer London 2000 1 Online-Ressource (150 p) txt rdacontent c rdamedia cr rdacarrier Lecture Notes in Control and Information Sciences 254 Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is presented: Their universal approximation ability is investigated- including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes. Finally, the complexity of training is considered - including new results on the loading problem for standard feedforward networks with an arbitrary multilayered architecture, a correlated number of neurons and training set size, a varying number of hidden neurons but fixed input dimension, or the sigmoidal activation function, respectively Engineering Control, Robotics, Mechatronics Control engineering Robotics Mechatronics Rekursives neuronales Netz (DE-588)4379549-3 gnd rswk-swf Maschinelles Lernen (DE-588)4193754-5 gnd rswk-swf Neuronales Netz (DE-588)4226127-2 gnd rswk-swf NP-vollständiges Problem (DE-588)4138229-8 gnd rswk-swf 1\p (DE-588)4113937-9 Hochschulschrift gnd-content Rekursives neuronales Netz (DE-588)4379549-3 s Maschinelles Lernen (DE-588)4193754-5 s NP-vollständiges Problem (DE-588)4138229-8 s 2\p DE-604 Neuronales Netz (DE-588)4226127-2 s 3\p DE-604 Erscheint auch als Druck-Ausgabe 9781852333430 https://doi.org/10.1007/BFb0110016 Verlag URL des Erstveröffentlichers Volltext 1\p cgwrk 20201028 DE-101 https://d-nb.info/provenance/plan#cgwrk 2\p cgwrk 20201028 DE-101 https://d-nb.info/provenance/plan#cgwrk 3\p cgwrk 20201028 DE-101 https://d-nb.info/provenance/plan#cgwrk |
| spellingShingle | Hammer, Barbara 1970- Learning with recurrent neural networks Engineering Control, Robotics, Mechatronics Control engineering Robotics Mechatronics Rekursives neuronales Netz (DE-588)4379549-3 gnd Maschinelles Lernen (DE-588)4193754-5 gnd Neuronales Netz (DE-588)4226127-2 gnd NP-vollständiges Problem (DE-588)4138229-8 gnd |
| subject_GND | (DE-588)4379549-3 (DE-588)4193754-5 (DE-588)4226127-2 (DE-588)4138229-8 (DE-588)4113937-9 |
| title | Learning with recurrent neural networks |
| title_auth | Learning with recurrent neural networks |
| title_exact_search | Learning with recurrent neural networks |
| title_full | Learning with recurrent neural networks by Barbara Hammer |
| title_fullStr | Learning with recurrent neural networks by Barbara Hammer |
| title_full_unstemmed | Learning with recurrent neural networks by Barbara Hammer |
| title_short | Learning with recurrent neural networks |
| title_sort | learning with recurrent neural networks |
| topic | Engineering Control, Robotics, Mechatronics Control engineering Robotics Mechatronics Rekursives neuronales Netz (DE-588)4379549-3 gnd Maschinelles Lernen (DE-588)4193754-5 gnd Neuronales Netz (DE-588)4226127-2 gnd NP-vollständiges Problem (DE-588)4138229-8 gnd |
| topic_facet | Engineering Control, Robotics, Mechatronics Control engineering Robotics Mechatronics Rekursives neuronales Netz Maschinelles Lernen Neuronales Netz NP-vollständiges Problem Hochschulschrift |
| url | https://doi.org/10.1007/BFb0110016 |
| work_keys_str_mv | AT hammerbarbara learningwithrecurrentneuralnetworks |