A Semantic Net Implemented With Synchronized Neurons for Binding and Inferencing

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" A Semantic Net Implemented With Synchronized Neurons for Binding and Inferencing "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	150387
Doc. No	:	ET22179
Main Entry	:	Mark Armand Atkins
Title Proper	:	A Semantic Net Implemented With Synchronized Neurons for Binding and Inferencing
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	A new computing architecture with the working name of S-96 is presented that is a tirsionof semantic networks and hficial neural systems. S-96 was intended to simultaneously overcomeseveral problems of conventional neural network architectures, especially "the binding problemn andconventional inability to incorporate knowledge, while retaining network homogeneity. It is not ahybrid system but rather a firsion system.The basic unit of the S- architecture is called the T-link, which is the neuralimpIementation of a single labeled semantic net link and its two c o ~ e ~ t ~ d nodes. The S-96implementation of a single T-link requires three types of sublinks and seven nodes that handle fivewave parameters simuttaneously. A background controller guides the flow of the network's focus ofattention and handles related tasks. The synchronization representation...,..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	:	TL45383.pdf
Title and statement of responsibility and	:	A Semantic Net Implemented With Synchronized Neurons for Binding and Inferencing [Thesis]