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 |
| Summary: | 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. |
|---|---|
| Item Description: | Gesehen am 06.03.2018 |
| Physical Description: | Online Resource |