Learning to Predict Non-Deterministically Generated Strings

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


In this article we present an algorithm that learns to predict non-deterministically generated strings. The problem of learning to predict non-deterministically generated strings was raised by Dietterich and Michalski (1986). While their objective was to give heuristic techniques that could be used to rapidly and effectively learn to predict a somewhat limited class of strings, our objective is to give an algorithm which, though impractical, is capable of learning to predict a very general class. Our algorithm is meant to provide a general framework within which heuristic techniques can be effectively employed.

Original languageEnglish
Pages (from-to)85-99
Number of pages15
JournalMachine Learning
Issue number1
StatePublished - Jul 1991


  • Kolmogorov complexity
  • Prediction
  • learning in the limit
  • minimum description length

Cite this