An Object-Relational Neural Network Database Type

E. Schikuta and P. Glantschnig (Austria)


List up to six key words here.


A framework for the conceptual and physical integration of neural networks into object-relational database systems is presented. The neural network ’meta model’, as the neural network paradigms, the static and dynamic properties, and the pattern description, is realized by a collection of ob jects, relations and dependencies between them. The spe cific network objects (the ’ortho’ networks) are objects in these relations. A handling scheme for the application data set, as input, output and training information, stored in the relational database together with the neural networks is de picted. Finally the implementation of the new NeuroOracle system based on the proposed framework is presented.

Important Links:

Go Back