Title :
Contribution to an XML-based representation of information related to artificial neural networks
Author_Institution :
Cologne Univ. of Appl. Sci., Cologne
Abstract :
This paper describes a scalable XML-based approach to store data and configurations of artificial neural networks (ANNs) for the purpose of documentation and exchange between scientific and production tools. After a brief summary on ANNs and how their information is currently stored, some use cases for data related to an ANN are discussed. Derived from these use cases, a specification for a flexible data storage solution is described. A subsequent section presents a complementary approach to store configuration information that also may be scaled to specific needs. Both specifications build up the XML language ANNSL (artificial neural network specification language).
Keywords :
XML; data handling; neural nets; specification languages; system documentation; XML language; XML-based representation; artificial neural network specification language; documentation; flexible data storage; Artificial neural networks; Data preprocessing; Documentation; Information analysis; Memory; Neurofeedback; Neurons; Production; Specification languages; XML;
Conference_Titel :
Industrial Electronics, 2008. IECON 2008. 34th Annual Conference of IEEE
Conference_Location :
Orlando, FL
Print_ISBN :
978-1-4244-1767-4
Electronic_ISBN :
1553-572X
DOI :
10.1109/IECON.2008.4758239