Universal prediction, i.e. Bayesian framework + Solomonoff prior + model class of all computable sequences, solves/avoids foundational problems of inductive inference, but has to be compromised in practice.

Skript bestehend aus den für die Vorlesung "Algorithmisches Lernen" (TU Darmstadt) relevanten Kapiteln der Dissertation "Selbsteinschätzende Lernverfahren: Möglichkeiten und Grenzen." von G. Grieser.

Solomonoff ’s induction method is a theoretical model of what could be considered a perfect inductive inference system. Incomputable.

A Unified Approach to Problems in Pattern Recognition and Artificial Intelligence.