A two-step algorithm for learning from unspecific reinforcement
We study a simple learning model based on the Hebb rule to cope with `delayed', unspecific reinforcement. In spite of the unspecific nature of the information-feedback, convergence to asymptotically perfect generalization is observed, with a rate depending, however, in a non-universal way on le...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
1999
|
| In: |
Journal of physics. A, Mathematical and theoretical
Year: 1999, Jahrgang: 32, Heft: 31 |
| ISSN: | 1751-8121 |
| DOI: | 10.1088/0305-4470/32/31/301 |
| Online-Zugang: | Verlag, Volltext: http://dx.doi.org/10.1088/0305-4470/32/31/301 Verlag, Volltext: http://stacks.iop.org/0305-4470/32/i=31/a=301 
|
| Verfasserangaben: | Reimer Kühn and Ion-Olimpiu Stamatescu |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1570439516 | ||
| 003 | DE-627 | ||
| 005 | 20220814085009.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 180306s1999 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1088/0305-4470/32/31/301 |2 doi | |
| 035 | |a (DE-627)1570439516 | ||
| 035 | |a (DE-576)500439516 | ||
| 035 | |a (DE-599)BSZ500439516 | ||
| 035 | |a (OCoLC)1340994000 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 29 |2 sdnb | ||
| 100 | 1 | |a Kühn, Reimer |e VerfasserIn |0 (DE-588)114014605X |0 (DE-627)898267560 |0 (DE-576)493682457 |4 aut | |
| 245 | 1 | 2 | |a A two-step algorithm for learning from unspecific reinforcement |c Reimer Kühn and Ion-Olimpiu Stamatescu |
| 264 | 1 | |c 1999 | |
| 300 | |a 13 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 06.03.2018 | ||
| 520 | |a We study a simple learning model based on the Hebb rule to cope with `delayed', unspecific reinforcement. In spite of the unspecific nature of the information-feedback, convergence to asymptotically perfect generalization is observed, with a rate depending, however, in a non-universal way on learning parameters. Asymptotic convergence can be as fast as that of Hebbian learning, but may be slower. Morever, for a certain range of parameter settings, it depends on initial conditions whether the system can reach the regime of asymptotically perfect generalization, or rather approaches a stationary state of poor generalization. | ||
| 700 | 1 | |a Stamatescu, Ion-Olimpiu |d 1941- |e VerfasserIn |0 (DE-588)1054303746 |0 (DE-627)791271358 |0 (DE-576)176705139 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Journal of physics. A, Mathematical and theoretical |d Bristol : IOP Publ., 2007 |g 32(1999,31) Artikel-Nummer 5749, 13 Seiten |h Online-Ressource |w (DE-627)225409631 |w (DE-600)1363010-6 |w (DE-576)077608011 |x 1751-8121 |7 nnas |a A two-step algorithm for learning from unspecific reinforcement |
| 773 | 1 | 8 | |g volume:32 |g year:1999 |g number:31 |g extent:13 |a A two-step algorithm for learning from unspecific reinforcement |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1088/0305-4470/32/31/301 |x Verlag |x Resolving-System |3 Volltext |
| 856 | 4 | 0 | |u http://stacks.iop.org/0305-4470/32/i=31/a=301 |x Verlag |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20180306 | ||
| 993 | |a Article | ||
| 994 | |a 1999 | ||
| 998 | |g 1054303746 |a Stamatescu, Ion-Olimpiu |m 1054303746:Stamatescu, Ion-Olimpiu |d 130000 |d 130300 |e 130000PS1054303746 |e 130300PS1054303746 |k 0/130000/ |k 1/130000/130300/ |p 2 |y j | ||
| 998 | |g 114014605X |a Kühn, Reimer |m 114014605X:Kühn, Reimer |d 130000 |d 130300 |e 130000PK114014605X |e 130300PK114014605X |k 0/130000/ |k 1/130000/130300/ |p 1 |x j | ||
| 999 | |a KXP-PPN1570439516 |e 3001712384 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"language":["eng"],"person":[{"display":"Kühn, Reimer","family":"Kühn","role":"aut","given":"Reimer"},{"role":"aut","given":"Ion-Olimpiu","display":"Stamatescu, Ion-Olimpiu","family":"Stamatescu"}],"id":{"doi":["10.1088/0305-4470/32/31/301"],"eki":["1570439516"]},"name":{"displayForm":["Reimer Kühn and Ion-Olimpiu Stamatescu"]},"physDesc":[{"extent":"13 S."}],"relHost":[{"type":{"media":"Online-Ressource","bibl":"periodical"},"disp":"A two-step algorithm for learning from unspecific reinforcementJournal of physics. A, Mathematical and theoretical","title":[{"title_sort":"Journal of physics","partname":"Mathematical and theoretical","subtitle":"concerned with the fundamental mathematical and computational methods underpinning physics, the journal is particularly relevant to statistical physics, chaotic and complex systems, classical and quantum mechanics and classical and quantum field theory","title":"Journal of physics"}],"pubHistory":["40.2007 -"],"note":["Gesehen am 29.06.2022"],"origin":[{"publisherPlace":"Bristol","dateIssuedDisp":"2007-","publisher":"IOP Publ.","dateIssuedKey":"2007"}],"id":{"eki":["225409631"],"zdb":["1363010-6"],"issn":["1751-8121"],"doi":["10.1088/issn.1751-8121"]},"recId":"225409631","physDesc":[{"extent":"Online-Ressource"}],"part":{"year":"1999","volume":"32","extent":"13","text":"32(1999,31) Artikel-Nummer 5749, 13 Seiten","issue":"31"},"titleAlt":[{"title":"Journal of physics / A"}],"language":["eng"]}],"recId":"1570439516","type":{"bibl":"article-journal","media":"Online-Ressource"},"note":["Gesehen am 06.03.2018"],"origin":[{"dateIssuedKey":"1999","dateIssuedDisp":"1999"}],"title":[{"title_sort":"two-step algorithm for learning from unspecific reinforcement","title":"A two-step algorithm for learning from unspecific reinforcement"}]} | ||
| SRT | |a KUEHNREIMETWOSTEPALG1999 | ||