Reflective Inductive Inference of Recursive Functions
- Gunter GrieserAffiliated withTechnische Universität Darmstadt, Fachbereich Informatik
In this paper, we investigate reflective inductive inference of recursive functions. A reflective IIM is a learning machine that is additionally able to assess its own competence.
First, we formalize reflective learning from arbitrary example sequences. Here, we arrive at four different types of reflection: reflection in the limit, optimistic, pessimistic and exact reflection.
Then, for learning in the limit, for consistent learning of three different types and for finite learning, we compare the learning power of reflective IIMs with each other as well as with the one of standard IIMs.
Finally, we compare reflective learning from arbitrary input sequences with reflective learning from canonical input sequences. In this context, an open question regarding total-consistent identification could be solved: it holds T-CONS a ⊂ T-CONS .
- Reflective Inductive Inference of Recursive Functions
- Book Title
- Algorithmic Learning Theory
- Book Subtitle
- 13th International Conference, ALT 2002 Lübeck, Germany, November 24–26, 2002 Proceedings
- pp 203-217
- Print ISBN
- Online ISBN
- Series Title
- Lecture Notes in Computer Science
- Series Volume
- Series ISSN
- Springer Berlin Heidelberg
- Copyright Holder
- Springer-Verlag Berlin Heidelberg
- Additional Links
- Industry Sectors
- eBook Packages
- Editor Affiliations
- 1. Dipartimento di Tecnologie dell’Informazione, Università degli Studi di Milano
- 2. Department of Computer Science, Tokyo Institute of Technology
- 3. Institut für Theoretische Informatik, Universität zu Lübeck
- Gunter Grieser (6)
- Author Affiliations
- 6. Technische Universität Darmstadt, Fachbereich Informatik, Alexanderstr. 10, 64283, Darmstadt, Germany
To view the rest of this content please follow the download PDF link above.