Refinement of approximate domain theories by knowledge-based neural networks

Authors:
Geoffrey G. Towell;Jude W. Shavlik;Michiel O. Noordewier
Affiliations:
University of Wisconsin - Madison, Madison, Wisconsin;University of Wisconsin - Madison, Madison, Wisconsin;University of Wisconsin - Madison, Madison, Wisconsin
Venue:
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Year:
1990

Citing 9
Cited 12

Quantitative results concerning the utility of explanation-based learning

Artificial Intelligence
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Symbolic and Neural Learning Algorithms: An Experimental Comparison

Machine Learning
A Study of Explanation-Based Methods for Inductive Learning

Machine Learning
Learning by Failing to Explain: Using Partial Explanations to Learn in Incomplete or Intractable Domains

Machine Learning
Explanation-Based Generalization: A Unifying View

Machine Learning
Induction of Decision Trees

Machine Learning
Explanation-Based Learning: An Alternative View

Machine Learning
Why are “what” and “where” processed by separate cortical visual systems? a computational investigation

Journal of Cognitive Neuroscience

Generalised RBF Networks Trained Using an IBL Algorithm for Mining Symbolic Data

PAKDD '01 Proceedings of the 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining
Knowledge based Least Squares Twin support vector machines

Information Sciences: an International Journal
Fraud detection model based on the discovery symbolic classification rules extracted from a neural network

MICAI'10 Proceedings of the 9th Mexican international conference on Artificial intelligence conference on Advances in soft computing: Part II
Short Communication: The prediction of promoter sequences based on the chemical features

Expert Systems with Applications: An International Journal
Predicate Logic Based Image Grammars for Complex Pattern Recognition

International Journal of Computer Vision
Review: Hybrid expert systems: A survey of current approaches and applications

Expert Systems with Applications: An International Journal
Theory refinement on Bayesian networks

UAI'91 Proceedings of the Seventh conference on Uncertainty in Artificial Intelligence
Knowledge-Rich similarity-based classification

ICCBR'05 Proceedings of the 6th international conference on Case-Based Reasoning Research and Development
Inductive bias strength in knowledge-based neural networks: application to magnetic resonance spectroscopy of breast tissues

Artificial Intelligence in Medicine
Paper: Polygenic trait analysis by neural network learning

Artificial Intelligence in Medicine
Extracting reducible knowledge from ANN with JBOS and FCANN approaches

Expert Systems with Applications: An International Journal
Central clustering of categorical data with automated feature weighting

IJCAI'13 Proceedings of the Twenty-Third international joint conference on Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Standard algorithms for explanation-based learning require complete and correct knowledge bases. The KBANN system relaxes this constraint through the use of empirical learning methods to refine approximately correct knowledge. This knowledge is used to determine the structure of an artificial neural network and the weights on its links, thereby making the knowledge accessible for modification by neural learning. KBANN is evaluated by empirical tests in the domain of molecular biology. Networks created by KBANN are shown to be superior, in terms of their ability to correctly classify unseen examples, to randomly initialized neural networks, decision trees, "nearest neighbor" matching, and standard techniques reported in the biological literature. In addition, KBANN'S networks improve the initial knowledge in biologically interesting ways.