Digraphs, Knowledge Hypernets, and Neurons

Preview

PDF
Neurons.pdf - Published
Download (150kB)

URL:	https://ub-madoc.bib.uni-mannheim.de/1662
URN:	urn:nbn:de:bsz:180-madoc-16629
Document Type:	Working paper
Year of publication:	2007
The title of a journal, publication series:	Manuskripte / Reihe Informatik
Place of publication:	Mannheim
Publication language:	English
Institution:	School of Business Informatics and Mathematics > Sonstige - Fakultät für Wirtschaftsinformatik und Wirtschaftsmathematik
MADOC publication series:	Veröffentlichungen der Fakultät für Mathematik und Informatik > Institut für Informatik > Technical Reports
Subject:	004 Computer science, internet
Subject headings (SWD):	Wissensbasiertes System , Neuronales Netz
Individual keywords (German):	Wissensbasiertes System, Neuronales Netz, Theorie des Lehrens und Lernens
Keywords (English):	knowledge system, neural network, theory of teaching/learning
Abstract:	A current flow network of switches, with input node I and output node O, are represented by a directed graph G. In G we define a model of a neuron, and introduce another model in which neurons are theoretically linked. In this second model, we cover invariance, information flow and noise. We show how this model arises from G, how it can be taught, and how it can be declaratively interpreted. The system is made dynamic due to the closing, from O to I, through the environment of the combined models, of a feedback circuit.
Additional information: