Bounding the cost of learned rules
نویسندگان
چکیده
In this article we approach one key aspect of the utility problem in explanationbased learning (EBL) | the expensive-rule problem | as an avoidable defect in the learning procedure. In particular, we examine the relationship between the cost of solving a problem without learning versus the cost of using a learned rule to provide the same solution, and refer to a learned rule as expensive if its use is more costly than the original problem solving from which it was learned. The key idea we explore is that expensiveness is inadvertently and unnecessarily introduced into learned rules by the learning algorithms themselves. This becomes a particularly powerful idea when combined with an analysis tool which identi es these hidden sources of expensiveness, and modi cations of the learning algorithms which eliminate them. The result is learning algorithms for which the cost of learned rules is bounded by the cost of the problem solving that they replace. We investigate this idea through an analysis of EBLSoar, an implementation of explanation-based learning within the Soar architecture. A transformational analysis is used to identify where EBLSoar inadvertently introduces substantial additional costs in the process of converting a problem solving episode into a learned rule | excessive costs which all ultimately turn out to stem from losses of information during learning. Based on these results, a modi ed EBLSoar algorithm| Bounded EBLSoar (BEBLSoar) | is developed from which all sources of expensiveness have been eliminated. The cost of using a rule learned by BEBLSoar is provably bounded by the cost of the problem solving it replaces.
منابع مشابه
Bounding the Cost of Learned Rules: A Transformational Approach
My dissertation research centers on application of machine learning techniques to speed up problem solving. In fact, many speed-up learning systems suffer from the utiliv problem; time after learning is greater than time before learning. Discovering how to assure that learned knowledge will in fact speed up system performance has been a focus of research in explanation-based learning (EBL). One...
متن کاملOn Passive Quadrupedal Bounding with Flexible Linear Torso
This paper studies the effect of flexible linear torso on the dynamics of passive quadruped bounding. A reduced-order passive and conservative model with linear flexible torso and springy legs is introduced. The model features extensive spine deformation during high-speed bounding, resembling those observed in a cheetah. Fixed points corresponding to cyclic bounding motions are found and calcul...
متن کاملAction recognition using saliency learned from recorded human gaze
This paper addresses the problem of recognition and localization of actions in image sequences, by utilizing, in the training phase only, gaze tracking data of people watching videos depicting the actions in question. First, we learn discriminative action features at the areas of gaze fixation and train a Convolutional Network that predicts areas of fixation (i.e. salient regions) from raw imag...
متن کاملA Sociological Study on the Effect of the Facebook for Bounding Social Capital among the Youth
Face book is virtual and cybernetic network which causes an effective force and among the youth. It shows that if the usage of the face book network increases at home the rate of the interaction and the bounding social capital decreases as well. It also indicates that the effect of face book usage among the young people has increased already. Through a questionnaire by a survey method, more tha...
متن کاملAutomatic Bounding Estimation in Modified Nlms Algorithm
Modified Normalized Least Mean Square (MNLMS) algorithm, which is a sign form of NLMS based on set-membership (SM) theory in the class of optimal bounding ellipsoid (OBE) algorithms, requires a priori knowledge of error bounds that is unknown in most applications. In a special but popular case of measurement noise, a simple algorithm has been proposed. With some simulation examples the performa...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Artif. Intell.
دوره 120 شماره
صفحات -
تاریخ انتشار 2000