A two-level evolution strategy balancing global and local search:
Abstract: "Evolution Strategies apply mutation and recombination operators in order to create their offspring. Both operators have a different role in the evolution process: recombination should combine information of different individuals, while mutation is performs [sic] a kind of random walk...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buch |
| Sprache: | English |
| Veröffentlicht: |
Amsterdam
1995
|
| Schriftenreihe: | Centrum voor Wiskunde en Informatica <Amsterdam> / Department of Computer Science: Report CS
95,59 |
| Schlagworte: | |
| Zusammenfassung: | Abstract: "Evolution Strategies apply mutation and recombination operators in order to create their offspring. Both operators have a different role in the evolution process: recombination should combine information of different individuals, while mutation is performs [sic] a kind of random walk to introduce new values. In an ES these operators are always applied together, but their different roles suggest that it might be better to apply them independently and at different rates. In order to do so the ES has been split into two levels. The resulting Modular Evolution Strategy consists of a population of local optimizers and a distributed population manager. Both parts have their own specific role in the optimization process. As a result of its modularity this method can be adapted more easily to specific classes of numerical optimization problems, and introduction of adaptive mechanisms is relatively easy. A further interesting aspect about this algorithm is that it does not need any global communication, and therefore can be parallelized easily. Many problems can be expressed as numerical optimization problems. Especially when the dimension of the input space and the number of local optima is high these problems tend to be very difficult. In order to obtain an efficient solver one has to gather information regarding the function to be optimized. Evolution based learning can be used to obtain this information. This paper contains results obtained with the Modular Evolution Strategy and compares these results to those obtained with other evolution based method [sic]. The results look promising." |
| Beschreibung: | 12 S. |
Internformat
MARC
| LEADER | 00000nam a2200000 cb4500 | ||
|---|---|---|---|
| 001 | BV011064400 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | t | ||
| 008 | 961118s1995 |||| 00||| engod | ||
| 035 | |a (OCoLC)35649323 | ||
| 035 | |a (DE-599)BVBBV011064400 | ||
| 040 | |a DE-604 |b ger |e rakddb | ||
| 041 | 0 | |a eng | |
| 100 | 1 | |a Kemenade, C. H. M. van |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a A two-level evolution strategy balancing global and local search |c C. H. M. van Kemenade |
| 264 | 1 | |a Amsterdam |c 1995 | |
| 300 | |a 12 S. | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b n |2 rdamedia | ||
| 338 | |b nc |2 rdacarrier | ||
| 490 | 1 | |a Centrum voor Wiskunde en Informatica <Amsterdam> / Department of Computer Science: Report CS |v 95,59 | |
| 520 | 3 | |a Abstract: "Evolution Strategies apply mutation and recombination operators in order to create their offspring. Both operators have a different role in the evolution process: recombination should combine information of different individuals, while mutation is performs [sic] a kind of random walk to introduce new values. In an ES these operators are always applied together, but their different roles suggest that it might be better to apply them independently and at different rates. In order to do so the ES has been split into two levels. The resulting Modular Evolution Strategy consists of a population of local optimizers and a distributed population manager. Both parts have their own specific role in the optimization process. As a result of its modularity this method can be adapted more easily to specific classes of numerical optimization problems, and introduction of adaptive mechanisms is relatively easy. A further interesting aspect about this algorithm is that it does not need any global communication, and therefore can be parallelized easily. Many problems can be expressed as numerical optimization problems. Especially when the dimension of the input space and the number of local optima is high these problems tend to be very difficult. In order to obtain an efficient solver one has to gather information regarding the function to be optimized. Evolution based learning can be used to obtain this information. This paper contains results obtained with the Modular Evolution Strategy and compares these results to those obtained with other evolution based method [sic]. The results look promising." | |
| 650 | 4 | |a Genetic algorithms | |
| 650 | 4 | |a Machine learning | |
| 650 | 4 | |a Mathematical optimization | |
| 810 | 2 | |a Department of Computer Science: Report CS |t Centrum voor Wiskunde en Informatica <Amsterdam> |v 95,59 |w (DE-604)BV008928356 |9 95,59 | |
| 999 | |a oai:aleph.bib-bvb.de:BVB01-007410355 | ||
Datensatz im Suchindex
| _version_ | 1804125553381343232 |
|---|---|
| any_adam_object | |
| author | Kemenade, C. H. M. van |
| author_facet | Kemenade, C. H. M. van |
| author_role | aut |
| author_sort | Kemenade, C. H. M. van |
| author_variant | c h m v k chmv chmvk |
| building | Verbundindex |
| bvnumber | BV011064400 |
| ctrlnum | (OCoLC)35649323 (DE-599)BVBBV011064400 |
| format | Book |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>02660nam a2200301 cb4500</leader><controlfield tag="001">BV011064400</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">t</controlfield><controlfield tag="008">961118s1995 |||| 00||| engod</controlfield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)35649323</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV011064400</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="100" ind1="1" ind2=" "><subfield code="a">Kemenade, C. H. M. van</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">A two-level evolution strategy balancing global and local search</subfield><subfield code="c">C. H. M. van Kemenade</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Amsterdam</subfield><subfield code="c">1995</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">12 S.</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">Centrum voor Wiskunde en Informatica <Amsterdam> / Department of Computer Science: Report CS</subfield><subfield code="v">95,59</subfield></datafield><datafield tag="520" ind1="3" ind2=" "><subfield code="a">Abstract: "Evolution Strategies apply mutation and recombination operators in order to create their offspring. Both operators have a different role in the evolution process: recombination should combine information of different individuals, while mutation is performs [sic] a kind of random walk to introduce new values. In an ES these operators are always applied together, but their different roles suggest that it might be better to apply them independently and at different rates. In order to do so the ES has been split into two levels. The resulting Modular Evolution Strategy consists of a population of local optimizers and a distributed population manager. Both parts have their own specific role in the optimization process. As a result of its modularity this method can be adapted more easily to specific classes of numerical optimization problems, and introduction of adaptive mechanisms is relatively easy. A further interesting aspect about this algorithm is that it does not need any global communication, and therefore can be parallelized easily. Many problems can be expressed as numerical optimization problems. Especially when the dimension of the input space and the number of local optima is high these problems tend to be very difficult. In order to obtain an efficient solver one has to gather information regarding the function to be optimized. Evolution based learning can be used to obtain this information. This paper contains results obtained with the Modular Evolution Strategy and compares these results to those obtained with other evolution based method [sic]. The results look promising."</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Genetic algorithms</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Machine learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Mathematical optimization</subfield></datafield><datafield tag="810" ind1="2" ind2=" "><subfield code="a">Department of Computer Science: Report CS</subfield><subfield code="t">Centrum voor Wiskunde en Informatica <Amsterdam></subfield><subfield code="v">95,59</subfield><subfield code="w">(DE-604)BV008928356</subfield><subfield code="9">95,59</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-007410355</subfield></datafield></record></collection> |
| id | DE-604.BV011064400 |
| illustrated | Not Illustrated |
| indexdate | 2024-07-09T18:03:23Z |
| institution | BVB |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-007410355 |
| oclc_num | 35649323 |
| open_access_boolean | |
| physical | 12 S. |
| publishDate | 1995 |
| publishDateSearch | 1995 |
| publishDateSort | 1995 |
| record_format | marc |
| series2 | Centrum voor Wiskunde en Informatica <Amsterdam> / Department of Computer Science: Report CS |
| spelling | Kemenade, C. H. M. van Verfasser aut A two-level evolution strategy balancing global and local search C. H. M. van Kemenade Amsterdam 1995 12 S. txt rdacontent n rdamedia nc rdacarrier Centrum voor Wiskunde en Informatica <Amsterdam> / Department of Computer Science: Report CS 95,59 Abstract: "Evolution Strategies apply mutation and recombination operators in order to create their offspring. Both operators have a different role in the evolution process: recombination should combine information of different individuals, while mutation is performs [sic] a kind of random walk to introduce new values. In an ES these operators are always applied together, but their different roles suggest that it might be better to apply them independently and at different rates. In order to do so the ES has been split into two levels. The resulting Modular Evolution Strategy consists of a population of local optimizers and a distributed population manager. Both parts have their own specific role in the optimization process. As a result of its modularity this method can be adapted more easily to specific classes of numerical optimization problems, and introduction of adaptive mechanisms is relatively easy. A further interesting aspect about this algorithm is that it does not need any global communication, and therefore can be parallelized easily. Many problems can be expressed as numerical optimization problems. Especially when the dimension of the input space and the number of local optima is high these problems tend to be very difficult. In order to obtain an efficient solver one has to gather information regarding the function to be optimized. Evolution based learning can be used to obtain this information. This paper contains results obtained with the Modular Evolution Strategy and compares these results to those obtained with other evolution based method [sic]. The results look promising." Genetic algorithms Machine learning Mathematical optimization Department of Computer Science: Report CS Centrum voor Wiskunde en Informatica <Amsterdam> 95,59 (DE-604)BV008928356 95,59 |
| spellingShingle | Kemenade, C. H. M. van A two-level evolution strategy balancing global and local search Genetic algorithms Machine learning Mathematical optimization |
| title | A two-level evolution strategy balancing global and local search |
| title_auth | A two-level evolution strategy balancing global and local search |
| title_exact_search | A two-level evolution strategy balancing global and local search |
| title_full | A two-level evolution strategy balancing global and local search C. H. M. van Kemenade |
| title_fullStr | A two-level evolution strategy balancing global and local search C. H. M. van Kemenade |
| title_full_unstemmed | A two-level evolution strategy balancing global and local search C. H. M. van Kemenade |
| title_short | A two-level evolution strategy balancing global and local search |
| title_sort | a two level evolution strategy balancing global and local search |
| topic | Genetic algorithms Machine learning Mathematical optimization |
| topic_facet | Genetic algorithms Machine learning Mathematical optimization |
| volume_link | (DE-604)BV008928356 |
| work_keys_str_mv | AT kemenadechmvan atwolevelevolutionstrategybalancingglobalandlocalsearch |