Learning decision trees from noisy examples:
Abstract: "We prove the learnability of decision trees of fixed rank in the presence of random classification noise. Ehrenfeucht and Haussler have presented an algorithm that learns decision trees of fixed rank probably approximately correctly from correct (noiseless) examples. We modify their...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Helsinki
1991
|
| Schriftenreihe: | Tietojenkäsittelyopin Laitos <Helsinki>: [Series of publications / A]
1991,3 |
| Schlagworte: | |
| Zusammenfassung: | Abstract: "We prove the learnability of decision trees of fixed rank in the presence of random classification noise. Ehrenfeucht and Haussler have presented an algorithm that learns decision trees of fixed rank probably approximately correctly from correct (noiseless) examples. We modify their algorithm slightly in order to achieve a noise-tolerant Occam algorithm for decision trees of fixed rank. Sakakibara has shown that the existence of a noise-tolerant Occam algorithm implies learnability in the presence of random classification noise. He has used this technique to prove the related result that decision lists are learnable from noisy examples." |
| Beschreibung: | 15 Bl. |
Internformat
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV010585958 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | t | ||
| 008 | 960125s1991 |||| 00||| engod | ||
| 035 | |a (OCoLC)31155446 | ||
| 035 | |a (DE-599)BVBBV010585958 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 049 | |a DE-91G | ||
| 100 | 1 | |a Elomaa, Tapio |d 1963- |e Verfasser |0 (DE-588)123914701 |4 aut | |
| 245 | 1 | 0 | |a Learning decision trees from noisy examples |c Tapio Elomaa ; Jyrki Kivinen |
| 264 | 1 | |a Helsinki |c 1991 | |
| 300 | |a 15 Bl. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a Tietojenkäsittelyopin Laitos <Helsinki>: [Series of publications / A] |v 1991,3 | |
| 520 | 3 | |a Abstract: "We prove the learnability of decision trees of fixed rank in the presence of random classification noise. Ehrenfeucht and Haussler have presented an algorithm that learns decision trees of fixed rank probably approximately correctly from correct (noiseless) examples. We modify their algorithm slightly in order to achieve a noise-tolerant Occam algorithm for decision trees of fixed rank. Sakakibara has shown that the existence of a noise-tolerant Occam algorithm implies learnability in the presence of random classification noise. He has used this technique to prove the related result that decision lists are learnable from noisy examples." | |
| 650 | 4 | |a Machine learning | |
| 700 | 1 | |a Kivinen, Jyrki |e Verfasser |4 aut | |
| 810 | 2 | |a A] |t Tietojenkäsittelyopin Laitos <Helsinki>: [Series of publications |v 1991,3 |w (DE-604)BV000904448 |9 1991,3 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-007058320 | ||
Datensatz im Suchindex
| _version_ | 1804125055869779968 |
|---|---|
| any_adam_object | |
| author | Elomaa, Tapio 1963- Kivinen, Jyrki |
| author_GND | (DE-588)123914701 |
| author_facet | Elomaa, Tapio 1963- Kivinen, Jyrki |
| author_role | aut aut |
| author_sort | Elomaa, Tapio 1963- |
| author_variant | t e te j k jk |
| building | Verbundindex |
| bvnumber | BV010585958 |
| ctrlnum | (OCoLC)31155446 (DE-599)BVBBV010585958 |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01646nam a2200301 cb4500</leader><controlfield tag="001">BV010585958</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">960125s1991 |||| 00||| engod</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)31155446</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV010585958</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rakddb</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="049" ind1=" " ind2=" "><subfield code="a">DE-91G</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Elomaa, Tapio</subfield><subfield code="d">1963-</subfield><subfield code="e">Verfasser</subfield><subfield code="0">(DE-588)123914701</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Learning decision trees from noisy examples</subfield><subfield code="c">Tapio Elomaa ; Jyrki Kivinen</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Helsinki</subfield><subfield code="c">1991</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">15 Bl.</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">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="490" ind1="1" ind2=" "><subfield code="a">Tietojenkäsittelyopin Laitos <Helsinki>: [Series of publications / A]</subfield><subfield code="v">1991,3</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "We prove the learnability of decision trees of fixed rank in the presence of random classification noise. Ehrenfeucht and Haussler have presented an algorithm that learns decision trees of fixed rank probably approximately correctly from correct (noiseless) examples. We modify their algorithm slightly in order to achieve a noise-tolerant Occam algorithm for decision trees of fixed rank. Sakakibara has shown that the existence of a noise-tolerant Occam algorithm implies learnability in the presence of random classification noise. He has used this technique to prove the related result that decision lists are learnable from noisy examples."</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kivinen, Jyrki</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="810" ind1="2" ind2=" "><subfield code="a">A]</subfield><subfield code="t">Tietojenkäsittelyopin Laitos <Helsinki>: [Series of publications</subfield><subfield code="v">1991,3</subfield><subfield code="w">(DE-604)BV000904448</subfield><subfield code="9">1991,3</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-007058320</subfield></datafield></record></collection> |
| id | DE-604.BV010585958 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-09T17:55:29Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-007058320 |
| oclc_num | 31155446 |
| open_access_boolean | |
| owner | DE-91G DE-BY-TUM |
| owner_facet | DE-91G DE-BY-TUM |
| physical | 15 Bl. |
| publishDate | 1991 |
| publishDateSearch | 1991 |
| publishDateSort | 1991 |
| record_format | marc |
| series2 | Tietojenkäsittelyopin Laitos <Helsinki>: [Series of publications / A] |
| spelling | Elomaa, Tapio 1963- Verfasser (DE-588)123914701 aut Learning decision trees from noisy examples Tapio Elomaa ; Jyrki Kivinen Helsinki 1991 15 Bl. txt rdacontent n rdamedia nc rdacarrier Tietojenkäsittelyopin Laitos <Helsinki>: [Series of publications / A] 1991,3 Abstract: "We prove the learnability of decision trees of fixed rank in the presence of random classification noise. Ehrenfeucht and Haussler have presented an algorithm that learns decision trees of fixed rank probably approximately correctly from correct (noiseless) examples. We modify their algorithm slightly in order to achieve a noise-tolerant Occam algorithm for decision trees of fixed rank. Sakakibara has shown that the existence of a noise-tolerant Occam algorithm implies learnability in the presence of random classification noise. He has used this technique to prove the related result that decision lists are learnable from noisy examples." Machine learning Kivinen, Jyrki Verfasser aut A] Tietojenkäsittelyopin Laitos <Helsinki>: [Series of publications 1991,3 (DE-604)BV000904448 1991,3 |
| spellingShingle | Elomaa, Tapio 1963- Kivinen, Jyrki Learning decision trees from noisy examples Machine learning |
| title | Learning decision trees from noisy examples |
| title_auth | Learning decision trees from noisy examples |
| title_exact_search | Learning decision trees from noisy examples |
| title_full | Learning decision trees from noisy examples Tapio Elomaa ; Jyrki Kivinen |
| title_fullStr | Learning decision trees from noisy examples Tapio Elomaa ; Jyrki Kivinen |
| title_full_unstemmed | Learning decision trees from noisy examples Tapio Elomaa ; Jyrki Kivinen |
| title_short | Learning decision trees from noisy examples |
| title_sort | learning decision trees from noisy examples |
| topic | Machine learning |
| topic_facet | Machine learning |
| volume_link | (DE-604)BV000904448 |
| work_keys_str_mv | AT elomaatapio learningdecisiontreesfromnoisyexamples AT kivinenjyrki learningdecisiontreesfromnoisyexamples |