Learning as Data Compression

Authors
Publication date 2007
Host editors
  • S.B. Cooper
  • B. Löwe
  • A. Sorbi
Book title Computation and Logic in the Real World
Book subtitle Third Conference on Computability in Europe, CiE 2007, Siena, Italy, June 18-23, 2007 : proceedings
ISBN
  • 9783540730002
ISBN (electronic)
  • 9783540730019
Series Lecture Notes in Computer Science
Event Third Conference on Computability in Europe, CiE 2007, Siena, Italy
Pages (from-to) 11-24
Publisher Berlin: Springer
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract In this paper I describe the general principles of learning as data compression. I introduce two-part code optimization and analyze the theoretical background in terms of Kolmogorov complexity. The good news is that the optimal compression theoretically represents the optimal interpretation of the data, the bad news is that such an optimal compression cannot be computed and that an increase in compression not necessarily implies a better theory. I discuss the application of these insights to DFA induction.
Document type Conference contribution
Language English
Published at https://doi.org/10.1007/978-3-540-73001-9_2
Permalink to this page
Back