|Title||Continuity of Semantic Operators in Logic Programming and their Approximation by Artificial Neural Networks.|
|Publication Type||Conference Paper|
|Year of Publication||2003|
|Authors||Anthony K. Seda, Pascal Hitzler|
|Conference Name||the 26th Annual German Conference on Artificial Intelligence, KI2003|
|Conference Location||Hamburg, Germany|
One approach to integrating First-order logic programming and neural network systems employs the approximation of semantic operators by feedforward networks. For this purpose, it is necessary to view these semantic operators as continuous functions on the reals. This can be accomplished by endowing the space of all interpretations of a logic program with topologies obtained from suitable embeddings. We will present such topologies which arise naturally out of the theory of logic programming, discuss continuity issues of several wellknown semantic operators, and derive some results concerning the approximation of these operators by feedforward neural networks.
|Full Text|| |
Anthony K. Seda and Pascal Hitzler, 'Continuity of Semantic Operators in Logic Programming and their Approximation by Artificial Neural Networks,' 26th Annual German Conference on Artificial Intelligence, KI2003, Hamburg, Germany, September 2003, pp. 105-119.