Statistical generalization of performance-related heuristics for knowledge-lean applications
نویسندگان
چکیده
In this paper, we present new results on the automated generalization of performance-related heuristics learned for knowledge-lean applications. By rst applying genetics-based learning to learn new heuristics for some small subsets of test cases in a problem space, we study methods to generalize these heuristics to unlearned subdomains of test cases. Our method uses a new statistical metric called probability of win. By assessing the performance of heuristics in a range-independent and distribution-independent manner, we can compare heuristics across problem subdomains in a consistent manner. To illustrate our approach, we show experimental results on generalizing heuristics learned for sequential circuit testing, VLSI cell placement and routing, branch-and-bound search, and blind equalization. We show that generalization can lead to new and robust heuristics that perform better than the original heuristics across test cases of diierent characteristics.
منابع مشابه
Teacher - an Automated System for Learning Knowledge-lean Heuristics
In this report, we present TEACHER, a system for learning knowledge-lean heuristics under resource constraints. TEACHER is an implementation of a genetics-based learning framework we have dev eloped for improving the performance of heuristics in application problem solvers. Besides providing a flexible and modular framework for conducting experiments, TEACHER provides (a) a test-bed for experim...
متن کاملTeacher: a Genetics-based System for Learning and for Generalizing Heuristics
In this chapter, we present the design of Teacher (an acronym for TEchniques for the Automated Creation of HEuRistics), a system for learning and for generalizing heuristics used in problem solving. Our system learns knowledge-lean heuristics whose performance is measured statistically. The objective of the design process is to nd, under resource constraints, improved heuristic methods (HMs) as...
متن کاملOn the generalization of Trapezoid Inequality for functions of two variables with bounded variation and applications
In this paper, a generalization of trapezoid inequality for functions of two independent variables with bounded variation and some applications are given.
متن کاملDynamics and generalization ability of LVQ algorithms Dynamics and generalization ability of LVQ algorithms
Learning vector quantization (LVQ) schemes constitute intuitive, powerful classification heuristics with numerous successful applications but, so far, limited theoretical background. We study LVQ rigorously within a simplifying model situation: two competing prototypes are trained from a sequence of examples drawn from a mixture of Gaussians. Concepts from statistical physics and the theory of ...
متن کاملCultural Competence: A Survey of Hospital Managers
Background and Objectives: Effective communication between managers and staff is a prerequisite to organization success. Cultural competence is key to effective communication. The aim of this study was to survey cultural competence in managers of selected hospitals. Methods: Twenty teaching hospital managers and four private hospital managers of senior level participated in the study. Data ...
متن کامل