خط مشی دسترسیدرباره ما
ثبت نامثبت نام
راهنماراهنما
فارسی
ورودورود
صفحه اصلیصفحه اصلی
جستجوی مدارک
تمام متن
منابع دیجیتالی
رکورد قبلیرکورد بعدی
Document Type : Latin Dissertation
Language of Document : English
Record Number : 150078
Doc. No : ET21870
Main Entry : Kevin Paul Grant
Title Proper : MACHINE LEARNING TECHNIQUES FOR EFFICIENT QUERY PROCESSING IN KNOWLEDGE BASE SYSTEMS
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : In this dissertation we propose a new technique for ecient query processing in knowledgebase systems. Query processing in knowledge base systems poses strong computational challengesbecause of the presence of combinatorial explosion. This arises because at any pointduring query processing there may be too many subqueries available for further exploration.Overcoming this diculty requires eective mechanisms for choosing from among these subqueriesgood subqueries for further processing.Inspired by existing works on stochastic logic programs, compositional modeling and probabilisticheuristic estimates we create a new, nondeterministic method to accomplish thetask of subquery selection for query processing. Specically, we use probabilistic heuristicestimates to make the necessary decisions. This approach combines subquery and knowledgebase properties and previous query processing experience with conditional probabilitytheory to derive a probability of success for each subquery. The probabilities of success areused to select the next subquery for further processing. The underlying, property-specicprobabilities of success are learned via a machine learning process involving a set of trainingsample queries.In this dissertation we present our new methodology and the algorithms used to accomplishboth the training and query processing phases of the system. We also present a method fordetermining the minimum training set size needed to achieve probability estimates with anydesired limit on the maximum size of the errors.,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject : Electericl tess
: برق
electronic file name : TL45061.pdf
Title and statement of responsibility and : MACHINE LEARNING TECHNIQUES FOR EFFICIENT QUERY PROCESSING IN KNOWLEDGE BASE SYSTEMS [Thesis]
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)