Improving Learning Performance Through Rational Resource Allocation

This article shows how rational analysis can be used to minimize learning cost for a general class of statistical learning problems. We discuss the factors that influence learning cost and show that the problem of effrcient learning can be cast as a resource optimization problem. Solutions found in this way can be significantly more efficient than the best solutions that do not account for these factors. We introduce a heuristic learning algorithm that approximately solves this optimization problem and document its performance improvements on synthetic and real-world problems. se1191]) of these factors to minimize learning cost. We discuss this in the context of parametric hypothesis selection , an abstract class of statistical learning problems where a system must select one of a finite set of hypothesized courses of action, where the quality of each hypothesis is described as a function of some unknown parameters (e.g. [Gratch92,Greiner92,Kaelbling93,Moore94,Musick93]). A learning s...

• Type: Conference
• Year: 1994
• Where: AAAI
• Authors: Jonathan Gratch, Steve A. Chien, Gerald DeJong
• Keywords: AAAI 1994, Heuristic Learning Algorithm, Intelligent Agents, Optimization Problem, Statistical Learning Problems