On Learning and Co-learning of Minimal Programs
- Freivalds, Karpinski and Smith [8] explored a special type of learning in the limit: identification of an unknown concept (function) by eliminating (erasing) all but one possible hypothesis (this type of learning is called co-learning). The motivation behind learning by erasing lies in the process of human and automated computer learning: often we can discard incorrect solutions much easier than to come up with the correct one. In Gödel numberings any learnable family can be learned by an erasing strategy. In this paper we concentrate on co-learning minimal programs. We show that co-learning of minimal programs, as originally defined is significantly weaker than learning minimal programs in Gödel numberings. In order to enhance the learning power
Verfasser*innenangaben: | Sanjay Jain, Efim Kinber, Rolf Wiehagen |
---|---|
URN: | urn:nbn:de:hbz:386-kluedo-481 |
Schriftenreihe (Bandnummer): | LSA Report (96,6E) |
Dokumentart: | Preprint |
Sprache der Veröffentlichung: | Englisch |
Jahr der Fertigstellung: | 1999 |
Jahr der Erstveröffentlichung: | 1999 |
Veröffentlichende Institution: | Technische Universität Kaiserslautern |
Datum der Publikation (Server): | 03.04.2000 |
Freies Schlagwort / Tag: | automated computer learning; co-learning |
Fachbereiche / Organisatorische Einheiten: | Kaiserslautern - Fachbereich Informatik |
DDC-Sachgruppen: | 0 Allgemeines, Informatik, Informationswissenschaft / 004 Informatik |
Lizenz (Deutsch): | Standard gemäß KLUEDO-Leitlinien vor dem 27.05.2011 |