Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik GmbH Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik GmbH scholarly article en Kötzing, Timo; Schirneck, Martin http://www.dagstuhl.de/lipics License
when quoting this document, please refer to the following
DOI:
URN: urn:nbn:de:0030-drops-57483
URL:

;

Towards an Atlas of Computational Learning Theory

pdf-format:


Abstract

A major part of our knowledge about Computational Learning stems from comparisons of the learning power of different learning criteria. These comparisons inform about trade-offs between learning restrictions and, more generally, learning settings; furthermore, they inform about what restrictions can be observed without losing learning power. With this paper we propose that one main focus of future research in Computational Learning should be on a structured approach to determine the relations of different learning criteria. In particular, we propose that, for small sets of learning criteria, all pairwise relations should be determined; these relations can then be easily depicted as a map, a diagram detailing the relations. Once we have maps for many relevant sets of learning criteria, the collection of these maps is an Atlas of Computational Learning Theory, informing at a glance about the landscape of computational learning just as a geographical atlas informs about the earth. In this paper we work toward this goal by providing three example maps, one pertaining to partially set-driven learning, and two pertaining to strongly monotone learning. These maps can serve as blueprints for future maps of similar base structure.

BibTeX - Entry

@InProceedings{ktzing_et_al:LIPIcs:2016:5748,
  author =	{Timo K{\"o}tzing and Martin Schirneck},
  title =	{{Towards an Atlas of Computational Learning Theory}},
  booktitle =	{33rd Symposium on Theoretical Aspects of Computer Science (STACS 2016)},
  pages =	{47:1--47:13},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-001-9},
  ISSN =	{1868-8969},
  year =	{2016},
  volume =	{47},
  editor =	{Nicolas Ollinger and Heribert Vollmer},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2016/5748},
  URN =		{urn:nbn:de:0030-drops-57483},
  doi =		{10.4230/LIPIcs.STACS.2016.47},
  annote =	{Keywords: computational learning, language learning, partially set-driven learning, strongly monotone learning}
}

Keywords: computational learning, language learning, partially set-driven learning, strongly monotone learning
Seminar: 33rd Symposium on Theoretical Aspects of Computer Science (STACS 2016)
Issue date: 2016
Date of publication: 2016


DROPS-Home | Fulltext Search | Imprint Published by LZI