Learning structured data from unspecific reinforcement

DOI10.1088/0305-4470/33/39/302MaRDI QIDQ4523639zbMATH OpenOpenAlexWikidataFDO

Authors R. Kühn, Ion-Olimpiu Stamatescu, Michael Biehl

Publication date 14 January 2001

Published in Journal of Physics A: Mathematical and General (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/0001405

zbMATH Keywords

delayedHebb rulelearing modelunspecific

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Memory and learning in psychology (91E40)

Abstract: We show that a straightforward extension of a simple learning model based on the Hebb rule, the previously introduced Association-Reinforcement-Hebb-Rule, can cope with "delayed", unspecific reinforcement also in the case of structured data and lead to perfect generalization.

Recommendations

• Corrigenda: ``Learning structured data from unspecific reinforcement
• Structured prediction with reinforcement learning
• Learning structures from data and experts
• scientific article; zbMATH DE number 67622
• Reinforcement learning with algorithms from probabilistic structure estimation

Cited in

(4)

• Structured patterns retrieval using a metric attractor network: application to fingerprint recognition
• Learning with incomplete information and the mathematical structure behind it
• Learning with incomplete information in the committee machine
• A two-step algorithm for learning from unspecific reinforcement

This page was built for publication: Learning structured data from unspecific reinforcement

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4523639)