The graph isomorphism problem: its structural complexity
The graph isomorphism problem: its structural complexity
Connectionist-Symbolic Integration: From Unified to Hybrid Approaches
Connectionist-Symbolic Integration: From Unified to Hybrid Approaches
Neural Networks and Structured Knowledge: Knowledge Representation and Reasoning
Applied Intelligence
Comparing Structures Using a Hopfield-Style Neural Network
Applied Intelligence
Massively Parallel Probabilistic Reasoning with Boltzmann Machines
Applied Intelligence
Approximating the Semantics of Logic Programs by Recurrent Neural Networks
Applied Intelligence
A Hybrid Architecture for Situated Learning of Reactive Sequential Decision Making
Applied Intelligence
The Connectionist Inductive Learning and Logic Programming System
Applied Intelligence
Wissensverarbeitung mit neuronalen Netzen
Grundlagen und Anwendungen der Künstlichen Intelligenz, 17. Fachtagung für Künstliche Intelligenz, Humboldt-Universität zu
Understanding neural networks via rule extraction
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
Rule extraction from linear support vector machines
Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining
On a hybrid weightless neural system
International Journal of Bio-Inspired Computation
Extracting reduced logic programs from artificial neural networks
Applied Intelligence
A new method for semi-automatic fuzzy training and its application in environmental modeling
Environmental Modelling & Software
Hi-index | 0.00 |
As the second part of a special issue on “Neural Networksand Structured Knowledge,” the contributions collected hereconcentrate on the extraction of knowledge, particularly in the formof rules, from neural networks, and on applications relying on therepresentation and processing of structured knowledge by neuralnetworks. The transformation of the low-level internal representationin a neural network into higher-level knowledge or information thatcan be interpreted more easily by humans and integrated withsymbol-oriented mechanisms is the subject of the first group ofpapers. The second group of papers uses specific applications asstarting point, and describes approaches based on neural networks forthe knowledge representation required to solve crucial tasks in therespective application.The companion first part of the special issue [1] contains papers dealing with representationand reasoning issues on the basis of neural networks.