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...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article (Journal) Chapter/Article |
| Language: | English |
| Published: |
1999
|
| In: |
Arxiv
|
| Online Access: | Verlag, kostenfrei, Volltext: http://arxiv.org/abs/cond-mat/9902354
|
| Author Notes: | Reimer Kühn, Ion-Olimpiu Stamatescu |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 157044059X | ||
| 003 | DE-627 | ||
| 005 | 20220814085020.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 180306s1999 xx |||||o 00| ||eng c | ||
| 035 | |a (DE-627)157044059X | ||
| 035 | |a (DE-576)50044059X | ||
| 035 | |a (DE-599)BSZ50044059X | ||
| 035 | |a (OCoLC)1340992876 | ||
| 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, 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. Moreover, 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. | ||
| 650 | 4 | |a Condensed Matter - Statistical Mechanics | |
| 650 | 4 | |a Condensed Matter - Disordered Systems and Neural Networks | |
| 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 Arxiv |d Ithaca, NY : Cornell University, 1991 |g (1999) Artikel-Nummer 9902354, 13 Seiten |h Online-Ressource |w (DE-627)509006531 |w (DE-600)2225896-6 |w (DE-576)28130436X |7 nnas |a A two step algorithm for learning from unspecific reinforcement |
| 773 | 1 | 8 | |g year:1999 |g extent:13 |a A two step algorithm for learning from unspecific reinforcement |
| 856 | 4 | 0 | |u http://arxiv.org/abs/cond-mat/9902354 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20180306 | ||
| 993 | |a Article | ||
| 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-PPN157044059X |e 3001714034 | ||
| BIB | |a Y | ||
| JSO | |a {"id":{"eki":["157044059X"]},"relHost":[{"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}],"part":{"year":"1999","text":"(1999) Artikel-Nummer 9902354, 13 Seiten","extent":"13"},"language":["eng"],"type":{"media":"Online-Ressource","bibl":"edited-book"},"disp":"A two step algorithm for learning from unspecific reinforcementArxiv","title":[{"title_sort":"Arxiv","title":"Arxiv"}],"origin":[{"publisherPlace":"Ithaca, NY ; [Erscheinungsort nicht ermittelbar]","dateIssuedDisp":"1991-","publisher":"Cornell University ; Arxiv.org","dateIssuedKey":"1991"}],"note":["Gesehen am 28.05.2024"],"pubHistory":["1991 -"],"id":{"zdb":["2225896-6"],"eki":["509006531"]},"physDesc":[{"extent":"Online-Ressource"}],"recId":"509006531"}],"recId":"157044059X","name":{"displayForm":["Reimer Kühn, Ion-Olimpiu Stamatescu"]},"physDesc":[{"extent":"13 S."}],"type":{"media":"Online-Ressource","bibl":"chapter"},"note":["Gesehen am 06.03.2018"],"origin":[{"dateIssuedKey":"1999","dateIssuedDisp":"1999"}],"title":[{"title":"A two step algorithm for learning from unspecific reinforcement","title_sort":"two step algorithm for learning from unspecific reinforcement"}],"language":["eng"],"person":[{"given":"Reimer","role":"aut","display":"Kühn, Reimer","family":"Kühn"},{"role":"aut","given":"Ion-Olimpiu","family":"Stamatescu","display":"Stamatescu, Ion-Olimpiu"}]} | ||
| SRT | |a KUEHNREIMETWOSTEPALG1999 | ||