|Reference classes, philosophy: is the set of objects, situations, or even data for which an expression stands and which can be exchanged with each other while the meaning of the expression and the context of its use are preserved. The so-called reference class problem arises when the class of the possible data is so extensive or so designed that several interpretations are possible which mutually exclude each other. See also reference system, uniqueness, indeterminacy, probability theory._____________Annotation: The above characterizations of concepts are neither definitions nor exhausting presentations of problems related to them. Instead, they are intended to give a short introduction to the contributions below. – Lexicon of Arguments. |
Peter Norvig on Reference Classes - Dictionary of Arguments
Norvig I 505
Reference class/Norvig/Russell: Reference class problem: The approach of choosing the “most specific” reference class of sufficient size was formally proposed by Reichenbach (1949)(1). Various attempts have been made, notably by Henry Kyburg (1977(2), 1983(3)), to formulate more sophisticated policies in order to avoid some obvious fallacies that arise with Reichenbach’s rule, but such approaches remain somewhat ad hoc. More recent work by Bacchus, Grove, Halpern, and Koller (1992)(4) extends Carnap’s methods to first-order theories, thereby avoiding many of the difficulties associated with the straightforward reference-class method. Kyburg and Teng (2006)(5) contrast probabilistic inference with nonmonotonic logic. >Probability theory/Norvig.
1. Reichenbach, H. (1949). The Theory of Probability: An Inquiry into the Logical and Mathematical
Foundations of the Calculus of Probability (second edition). University of California Press
2. Kyburg, H. E. (1977). Randomness and the right reference class. J. Philosophy, 74(9), 501-521.
3. Kyburg, H. E. (1983). The reference class. Philosophy of Science, 50, 374–397.
4. Bacchus, F., Grove, A., Halpern, J. Y., and Koller, D. (1992). From statistics to beliefs. In AAAI-92,
5. Kyburg, H. E. and Teng, C.-M. (2006). Nonmonotonic logic and statistical inference. Computational
Intelligence, 22(1), 26-51_____________Explanation of symbols: Roman numerals indicate the source, arabic numerals indicate the page number. The corresponding books are indicated on the right hand side. ((s)…): Comment by the sender of the contribution. Translations: Dictionary of Arguments The note [Author1]Vs[Author2] or [Author]Vs[term] is an addition from the Dictionary of Arguments. If a German edition is specified, the page numbers refer to this edition.
Stuart J. Russell
Artificial Intelligence: A Modern Approach Upper Saddle River, NJ 2010