A Syntactic Characterization of Bounded-Rank Decision Trees in Terms of Decision Lists
نویسنده
چکیده
Decision lists and decision trees are two models of computation for boolean functions. that rank-k decision trees are a subclass of decision lists. Here we identify precisely, by giving a syntactical characterization, the subclass of decision lists which correspond exactly to the class of bounded rank decision trees. Furthermore we give a more general algorithm to recover reduced decision trees from decision lists.
منابع مشابه
A New Algorithm for Optimization of Fuzzy Decision Tree in Data Mining
Decision-tree algorithms provide one of the most popular methodologies for symbolic knowledge acquisition. The resulting knowledge, a symbolic decision tree along with a simple inference mechanism, has been praised for comprehensibility. The most comprehensible decision trees have been designed for perfect symbolic data. Classical crisp decision trees (DT) are widely applied to classification t...
متن کاملRank-r Decision Trees are a Subclass of r-Decision Lists
Rivcst [5] defines the notion of a decision list as a representation for Boolean functions. He shows that k-decision lists, a generalization of k-CNF and k-DNF formulas, are learnable for constant k in the PAC (or distribution-free) learning model [&,3]. Ehrenfcucht and Haussler [l] define the notion of the rank of a decision tree, and prove that decision trees of constant rank are also learnab...
متن کاملPredicting The Type of Malaria Using Classification and Regression Decision Trees
Predicting The Type of Malaria Using Classification and Regression Decision Trees Maryam Ashoori1 *, Fatemeh Hamzavi2 1School of Technical and Engineering, Higher Educational Complex of Saravan, Saravan, Iran 2School of Agriculture, Higher Educational Complex of Saravan, Saravan, Iran Abstract Background: Malaria is an infectious disease infecting 200 - 300 million people annually. Environme...
متن کاملCOMS 6253 : Advanced
Previously: • Administrative basics, introduction and high-level overview • Concept classes and the relationships among them: DNF formulas, decision trees, decision lists, linear and polynomial threshold functions. • The Probably Approximately Correct (PAC) learning model. • PAC learning linear threshold functions in poly(n, 1/ , log 1/δ) time • PAC learning polynomial threshold functions. Toda...
متن کاملOn the Isomorphism Problem for Decision Trees and Decision Lists
We study the complexity of isomorphism testing for boolean functions that are represented by decision trees or decision lists. Our results are the following: • Isomorphism testing of rank 1 decision trees is complete for logspace. • For any constant r ≥ 2, isomorphism testing for rank r decision trees is polynomial-time equivalent to Graph Isomorphism. As a consequence of our reduction, we obta...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- ITA
دوره 31 شماره
صفحات -
تاریخ انتشار 1997