Optimization problem in inductive inference
Algorithms recognizing to which of n classes some total function belongs are constructed (n > 2). In this construction strategies determining to which of two classes the function belongs are used as subroutines. Upper and lower bounds for number of necessary strategies are obtained in several models: FIN- and EX-identification and EX-identification with limited number of mindchanges. It is proved that in EX-identification it is necessary to use n(n−1)/2 strategies. In FIN-identification [3n/2 − 2] strategies are necessary and sufficient, in EX-identification with one mindchange- n log2n+o(n log2n) strategies.
Unable to display preview. Download preview PDF.
- M.Velauthapillai, W.I.Gasarch and M.G.Pleszkoch, Classification Using Information. This book.Google Scholar
- R.Freivalds, Inductive Inference of Recursive Functions Qualitative Theory. Baltic Computer Science. Lecture Notes in Computer Science, Vol. 502 (1991), pp. 77–110.Google Scholar
- M.Hall, Combinatorial Theory. Blaisdell Publishing Company,1967.Google Scholar
- W.Sierpinski, Elementary Theory of Numbers. North-Holland,1988.Google Scholar