TECHNIQUES IN NEURAL NETWORK TRAINING WITH AN ENHANCED ROBUSTNESS

منو

" TECHNIQUES IN NEURAL NETWORK TRAINING WITH AN ENHANCED ROBUSTNESS "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	149638
Doc. No	:	ET21430
Main Entry	:	Milos Manic
Title Proper	:	TECHNIQUES IN NEURAL NETWORK TRAINING WITH AN ENHANCED ROBUSTNESS
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Since the pio~ering work of McCulloch and Pitts from early 1940-ies and introduction ofthe concept of artificial neuron, numerous attempts aiming to automate the process oftraining neural networks have been made. Neural networks, though successfully applied inmany different areas still bear significant convergence problems with respect to adequatechoice of network parameters, architecture, initial set of weights, and other governingparameters.The goal of dissertation was to develop different approaches in iterative search to achievefast and robust.
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL44591.pdf
Title and statement of responsibility and	:	TECHNIQUES IN NEURAL NETWORK TRAINING WITH AN ENHANCED ROBUSTNESS [Thesis]