An Information-Theoretic Approach to Artificial Neural Networks: Applications in Geographic Information Processing

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" An Information-Theoretic Approach to Artificial Neural Networks: Applications in Geographic Information Processing "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	151689
Doc. No	:	ET23481
Main Entry	:	Chih-Chung Kao
Title Proper	:	An Information-Theoretic Approach to Artificial Neural Networks: Applications in Geographic Information Processing
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Information-theoretic approaches to neural networks provide alternative ways ofcontrolling network complexity through optimizing the mutual information or erltropy ofneural networks, based on Shannon's information theory. There are three primaryapproaches to training information-theoretic neural networks, i-e., the infomar principle(maximizing mutual information), the maximum entropy method, and the cross-entropymethod. Following Linsker's Irfloma~ principte (2988), many studies have claimed thatthe Ilrfoma~ principle is the basis of their theoretical foundation. However, a literaturereview shows that many studies of information-theoretic neural networks are vague abouttheir theoretical foundation.Therefore, this dissertation finds its motivation from the diversity of information-theoretic models in the literature and works to develop an information-theoretic model......-....,....-...,..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	:	TL46722.pdf
Title and statement of responsibility and	:	An Information-Theoretic Approach to Artificial Neural Networks: Applications in Geographic Information Processing [Thesis]