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 : 149741
Doc. No : ET21533
Main Entry : Bernard Rosell
Title Proper : EXTENDED BAYES AND SKEWING: ON TWO IMPROVEMENTS TO STANDARD INDUCTION-BASED LEARNING ALGORITHMS
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : We address improvements to Naive Bayes (NB) and Decision Trees, two standard induction-based methods for solving classification problems. The goal of these improvements is to extractmore information from the training examples, in order to more accurately classify new examples.The first part of this thesis presents a new learning algorithm, Extended Bayes (EB), which is anextension of NB. NB classifies new examples using conditional probabilities computed from thetraining data. It is simple, fast, and widely applicable. EB retains these positive properties of NB,while equaling ortested 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 : TL44706.pdf
Title and statement of responsibility and : EXTENDED BAYES AND SKEWING: ON TWO IMPROVEMENTS TO STANDARD INDUCTION-BASED LEARNING ALGORITHMS [Thesis]
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)