Corpus ID: 1095793

RULEX & CEBP Networks As the Basis for a Rule Refinement System

@inproceedings{Andrews1995RULEXC,
  title={RULEX \& CEBP Networks As the Basis for a Rule Refinement System},
  author={R. Andrews and S. Geva},
  year={1995}
}
In artificial intelli gence, knowledge is often represented as a set of rules to be interpreted by an expert system. This rule base is garnered from the knowledge of a domain expert and, for a variety of reasons, may be incomplete, contradictory, or inaccurate. A system using these rules is also static and unable to learn new rules or modify existing rules in the problem domain. In this paper we describe the Constrained Error Backpropagation, (CEBP), Multi Layer Perceptron, an Artificial Neural… Expand

Figures from this paper

Refining Expert Knowledge with an Artificial Neural Network
This paper describes RULEIN/RULEX; an automated technique for the refinement of a knowledge base. RULEIN constructs a Rapid Backprop (RBP) network from an initial, partially complete/accurateExpand
An automated rule refinement system
TLDR
RULEX, a technique designed to provide an explanation component for its underlying Local Cluster ANN through the extraction of symbolic rules from the weights of the local cluster units of the trained ANN, and RULEIN, a rule refinement technique that allows symbolic rules to be converted into the parameters that define local cluster functions. Expand
Neural Network Based Agent for Discover ing Rules in M edical Databases
Neural network based agents were trained on incomplete sets of classified instances that experienced doctors could suggest. Trained neural networks correctly classified the presented examples. A userExpand
Characterization of the Wisconsin Breast cancerDatabase Using a Hybrid Symbolic -
E xtracting rules from trained artiicial neural networks adds more powerful features to their output decisions. The explanation, validation, and cross-referencing are some of these powerful features.Expand
The truth is in there : directions and challenges in extracting rules from trained ar tificial neural networks
A recognized impediment to the more widespread utilisation of Artificial Neural Networks (ANNs) is the absence of a capability to explain, in a humancomprehensible form, either the process by which aExpand
FRULEX-Fuzzy Rules Extraction Using Rapid Back Propagation Neural Networks
In this paper, we present a new approach for extracting fuzzy rules from numerical input–output data for pattern classification. The approach combines the merits of the fuzzy logic theory, and neuralExpand
Rule Extraction from Neural Networks
The artificial neural networks (ANNs) are well suitable to solve a variety class of problems in a knowledge discovery field (e.g., in natural language processing) because the trained networks areExpand
Neural network explanation using inversion
TLDR
HYPINV is the only pedagogical rule extraction method, which extracts hyperplane rules from continuous or binary attribute neural networks, and it is able to generate rules with arbitrarily desired fidelity, maintaining a fidelity-complexity tradeoff. Expand
Rules and Local Function Networks
TLDR
This paper presents an overview of rule extraction and rule refinement techniques that have been developed specifically for use with local function networks, artificial neural networks that make use of some form of local response units in their hidden layer. Expand
Rule Extraction From Dynamic Cell Structure Neural Network Used in a Safety Critical Application
TLDR
The intelligent flight control application of the DCS is explained, the method used for rule extraction is described, experimental results of the rule extraction techniques applied to several data sets are provided, and the relevance of the rules to the V&V process is examined. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 25 REFERENCES
Extracting Provably Correct Rules from Artificial Neural Networks
TLDR
This paper describes an approach to neural network rule extraction based on Validity Interval Analysis (VI-Analysis), a generic tool for extracting symbolic knowledge from Backpropagation-style artificial neural networks and describes techniques for generating and testing rule hypotheses. Expand
Refinement of approximate domain theories by knowledge-based neural networks
TLDR
The KBANN system relaxes this constraint through the use of empirical learning methods to refine approximately correct knowledge, 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. Expand
Rule Generation from Neural Networks
  • Limin Fu
  • Computer Science
  • IEEE Trans. Syst. Man Cybern. Syst.
  • 1994
TLDR
This paper shows how to interpret neural network knowledge in symbolic form, lay dawn required definitions for this treatment, formulate the interpretation algorithm, and formally verify its soundness. Expand
Extraction, Insertion and Refinement of Symbolic Rules in Dynamically Driven Recurrent Neural Networks
TLDR
This paper discusses various issues: how rules are inserted into recurrent networks, how they affect training and generalization, and how those rules can be checked and corrected. Expand
Using Sampling and Queries to Extract Rules from Trained Neural Networks
TLDR
This work presents a novel method that casts rule extraction not as a search problem, but instead as a learning problem, and exploits the property that networks can be efficiently queried. Expand
Medical diagnostic expert system based on PDP model
  • K. Saito, R. Nakano
  • Computer Science
  • IEEE 1988 International Conference on Neural Networks
  • 1988
TLDR
The applicability of PDP (parallel distributed processing) models to knowledge processing is clarified and a method to extract rules from the network and usage of the rules in a confirmation process are proposed. Expand
Rule Learning by Searching on Adapted Nets
TLDR
The KT algonhm is a novel algonthm for generating rules from an adapted net efficiently that is able to deal with both single-layer and multi-layer networks, and can learn both confirming and disconfirming rules. Expand
Medical Diagnostic Expert System
TLDR
It is shown here that matrix memory models with associations modulated by context can perform automatic medical diagnosis and is a highly promising alternative in the development of accuracy diagnostic tools. Expand
A constructive method for multivariate function approximation by multilayer perceptrons
TLDR
It is shown how to construct a perceptron with two hidden layers for multivariate function approximation, which can perform function approximation in the same manner as networks based on Gaussian potential functions, by linear combination of local functions. Expand
The MONK''s Problems-A Performance Comparison of Different Learning Algorithms, CMU-CS-91-197, Sch
An improved liquid vehicle for a pharmaceutical composition of a mixture of propylene glycol and glycerine, a novel pharmaceutical composition of theophylline and this vehicle, comprising aExpand
...
1
2
3
...