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 : 152249
Doc. No : ET24041
Main Entry : Joshua E. Menke
Title Proper : IMPROVING MACHINE LEARNING THROUGH ORACLE LEARNING
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : The following dissertation presents a new paradigm for improving the trainingof machine learning algorithms, oracle learning. The main idea in oracle learningis that instead of training directly on a set of data, a learning model is trained toapproximate a given oracle's behavior on a set of data. This can be beneficial insituations where it is easier to obtain an oracle than it is to use it at application time.It is shown that oracle learning can be applied to more effectively reduce the size ofartificial neural networks, to more efficiently take advantage of domain experts byapproximating them, and to adapt a problem more effectively to a machine learningalgorithm..
Subject : Electericl tess
: برق
electronic file name : TL48195.pdf
Title and statement of responsibility and : IMPROVING MACHINE LEARNING THROUGH ORACLE LEARNING [Thesis]
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)