Title :
An overview on supervised neural networks for structures
Author :
Sperduti, Alessandro
Author_Institution :
Dipartimento di Inf., Pisa Univ., Italy
Abstract :
In recent years neural networks for the representation and processing of structures have been developed. These kind of networks are of paramount importance for the development of hybrid systems, since they allow the treatment of structured information very naturally and, in several cases, very efficiently. We present the basic concepts underpinning this class of networks and discuss computational and complexity issues
Keywords :
computational complexity; directed graphs; finite state machines; learning (artificial intelligence); neural nets; complexity; hybrid systems; structured information; structures; supervised neural networks; Computational intelligence; Computer networks; Encoding; Expert systems; Fuzzy logic; Genetic algorithms; Hybrid intelligent systems; Intelligent networks; Neural networks; Tree graphs;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.614701
