Title :
Optimized rule induction
Author :
Weiss, Sholom M. ; Indurkhya, Nitin
Author_Institution :
Rutgers Univ., New Brunswick, NJ, USA
Abstract :
Swap-1, a state-of-the-art system for learning decision rules from data, is presented. The method embodied in Swap-1 generates reduced-complexity solutions by inducing compact solutions in larger dimensions where many rules might be needed to make accurate predictions. For many applications, such systems can automatically construct relatively compact rule sets with highly predictive performance.<>
Keywords :
computational complexity; inference mechanisms; learning (artificial intelligence); learning systems; optimisation; Swap-1; accurate predictions; compact rule sets; compact solutions; decision rule learning; optimized rule induction; predictive performance; reduced-complexity solutions; Accuracy; Character recognition; Classification tree analysis; Databases; Decision trees; Intelligent systems; Learning systems; Neural networks; Parameter estimation; Predictive models;
Journal_Title :
IEEE Expert
