Multilayer feedforward networks are universal approximators
Neural Networks
Recursive distributed representations
Artificial Intelligence - On connectionist symbol processing
Artificial Intelligence - On connectionist symbol processing
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Knowledge-based artificial neural networks
Artificial Intelligence
Knowledge-based neurocomputing
Knowledge-based neurocomputing
Symbolic knowledge extraction from trained neural networks: a sound approach
Artificial Intelligence
Artificial nonmonotonic neural networks
Artificial Intelligence
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Neural Networks in Computer Intelligence
Neural Networks in Computer Intelligence
Approximate Match of Rules Using Backpropagation Neural Networks
Machine Learning
Connectionist-Symbolic Integration: From Unified to Hybrid Approaches
Connectionist-Symbolic Integration: From Unified to Hybrid Approaches
Neural-Symbolic Learning System: Foundations and Applications
Neural-Symbolic Learning System: Foundations and Applications
Approximating the Semantics of Logic Programs by Recurrent Neural Networks
Applied Intelligence
Three problems in computer science
Journal of the ACM (JACM)
CHCL - A Connectionist Infernce System
Proceedings of the International Workshop on Parallelization in Inference Systems
On constructing fibred tableaux for BDI logics
PRICAI'06 Proceedings of the 9th Pacific Rim international conference on Artificial intelligence
Extracting reduced logic programs from artificial neural networks
Applied Intelligence
A fibred tableau calculus for modal logics of agents
DALT'06 Proceedings of the 4th international conference on Declarative Agent Languages and Technologies
Fewer epistemological challenges for connectionism
CiE'05 Proceedings of the First international conference on Computability in Europe: new Computational Paradigms
| Hi-index | 0.00 |
Neural-symbolic systems are hybrid systems that integrate symbolic logic and neural networks. The goal of neural-symbolic integration is to benefit from the combination of features of the symbolic and connectionist paradigms of artificial intelligence. This paper introduces a new neural network architecture based on the idea of fibring logical systems. Fibring allows one to combine different logical systems in a principled way. Fibred neural networks may be composed not only of interconnected neurons but also of other networks, forming a recursive architecture. A fibring function then defines how this recursive architecture must behave by defining how the networks in the ensemble relate to each other, typically by allowing the activation of neurons in one network (A) to influence the change of weights in another network (B). Intuitively, this can be seen as training network B at the same time that one runs network A. We show that, in addition to being universal approximators like standard feedforward networks, fibred neural networks can approximate any polynomial function to any desired degree of accuracy, thus being more expressive than standard feedforward networks.