Upper Bounds on Complexity and Algorithms for Construction of Deterministic Decision Trees for Decision Tables. First Approach
- 9 Downloads
In this chapter, for complexity functions having the properties \(\varLambda 1 \), \(\varLambda 2\), and \(\varLambda 3\), upper bounds on the minimum complexity and algorithms for construction of deterministic decision trees for decision tables are considered. These bounds and algorithms are based on the use of so-called difference-bounded uncertainty measures for decision tables.
- 2.Moshkov, M.: Conditional tests. In: Yablonskii, S.V. (ed.) Problemy Kibernetiki (in Russian), vol. 40, pp. 131–170. Nauka Publishers, Moscow (1983)Google Scholar
- 3.Moshkov, M.: Bounds on complexity and algorithms for construction of deterministic conditional tests. In: Mat. Vopr. Kibern. (in Russian), vol. 16, pp. 79–124. Fizmatlit, Moscow (2007). http://library.keldysh.ru/mvk.asp?id=2007-79
- 4.Quinlan, J.R.: Discovering rules by induction from large collections of examples. In: D. Michie (ed.) Experts Systems in the Microelectronic Age, pp. 168–201. Edinburg University Press (1979)Google Scholar