The cascade-correlation learning architecture
Advances in neural information processing systems 2
Constructing hidden units using examples and queries
NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
The Utility of Knowledge in Inductive Learning
Machine Learning
Generative learning structures and processes for generalized connectionist networks
Information Sciences: an International Journal
Extracting Refined Rules from Knowledge-Based Neural Networks
Machine Learning
Theory refinement combining analytical and empirical methods
Artificial Intelligence
Knowledge-based artificial neural networks
Artificial Intelligence
Automated Refinement of First-Order Horn-Clause Domain Theories
Machine Learning
Elements of machine learning
Software agents
Fundamentals of Artificial Neural Networks
Fundamentals of Artificial Neural Networks
Machine Learning
Pattern Recognition and Neural Networks
Pattern Recognition and Neural Networks
Artificial Intelligence and the Design of Expert Systems
Artificial Intelligence and the Design of Expert Systems
Machine Learning
An Information-Theoretic Definition of Similarity
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Extracting comprehensible models from trained neural networks
Extracting comprehensible models from trained neural networks
Bias-driven revision of logical domain theories
Journal of Artificial Intelligence Research
Connectionist theory refinement: genetically searching the space of network topologies
Journal of Artificial Intelligence Research
Rerepresenting and restructuring domain theories: a constructive induction approach
Journal of Artificial Intelligence Research
Hi-index | 0.00 |
Knowledge based artificial neural networks offer an attractive approach to extending or modifying incomplete knowledge bases or domain theories through a process of data-driven theory refinement. We present an efficient algorithm for data-driven knowledge discovery and theory refinement using DistAl, a novel (inter-pattern distance based, polynomial time) constructive neural network learning algorithm. The initial domain theory comprising of propositional rules is translated into a knowledge based network. The domain theory is modified using DistAl which adds new neurons to the existing network as needed to reduce classification errors associated with the incomplete domain theory on labeled training examples. The proposed algorithm is capable of handling patterns represented using binary, nominal, as well as numeric (real-valued) attributes. Results of experiments on several datasets for financial advisor and the human genome project indicate that the performance of the proposed algorithm compares quite favorably with other algorithms for connectionist theory refinement (including those that require substantially more computational resources) both in terms of generalization accuracy and network size.