Rule extraction from recurrent neural networks using a symbolic machine learning algorithm

Vahed, Amir Taghizadeh; Omlin, Christian W.

doi:10.1109/iconip.1999.845683

Cited by 14 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vahed and Omlin [323] used a symbolic learning algorithm with polynomial time to extract rules solely based on changes in inputs and outputs of a trained network. The clustering phase is eliminated in this rule extraction approach, which increases the fidelity of the extracted knowledge.…”

Section: Rule Extraction Based On Neural Network Classifiersmentioning

confidence: 99%

Data Mining with Computational Intelligence

Wang¹

2005

Advanced Information and Knowledge Processing

141

View full text Add to dashboard Cite

Section: Rule Extraction Based On Neural Network Classifiersmentioning

confidence: 99%

Data Mining with Computational Intelligence

Wang¹

2005

Advanced Information and Knowledge Processing

141

View full text Add to dashboard Cite

“…Vahed and Omlin [99] use a polynomial-time, symbolic learning algorithm to infer DFA's solely based on observation of a trained network's input-output behavior. This is a pedagogical approach and produces a minimal representation of the DFA.…”

Section: B Neural Modelsmentioning

confidence: 99%

Neuro-fuzzy rule generation: survey in soft computing framework

Mitra

Hayashi

2000

IEEE Trans. Neural Netw.

628

235

View full text Add to dashboard Cite

The present article is a novel attempt in providing an exhaustive survey of neuro-fuzzy rule generation algorithms. Rule generation from artificial neural networks is gaining in popularity in recent times due to its capability of providing some insight to the user about the symbolic knowledge embedded within the network. Fuzzy sets are an aid in providing this information in a more human comprehensible or natural form, and can handle uncertainties at various levels. The neuro-fuzzy approach, symbiotically combining the merits of connectionist and fuzzy approaches, constitutes a key component of soft computing at this stage. To date, there has been no detailed and integrated categorization of the various neuro-fuzzy models used for rule generation. We propose to bring these together under a unified soft computing framework. Moreover, we include both rule extraction and rule refinement in the broader perspective of rule generation. Rules learned and generated for fuzzy reasoning and fuzzy control are also considered from this wider viewpoint. Models are grouped on the basis of their level of neuro-fuzzy synthesis. Use of other soft computing tools like genetic algorithms and rough sets are emphasized. Rule generation from fuzzy knowledge-based networks, which initially encode some crude domain knowledge, are found to result in more refined rules. Finally, real-life application to medical diagnosis is provided.

show abstract

“…Moreover, the reasoning direction is always from the inputs to the outputs of the ANN. To overcome these problems, the extraction of rules, for example, propositional or fuzzy rules, has been considered (see Das and Das, 1991;Ghosh, 1996, 1999;Vahed and Omlin, 1999;and D'Avila Garcez et al, 2001). In the following we describe a black box approach to rule extraction that can be used for extracting rules from various different neural network topologies.…”

Section: Compiling Neural Network Into Qualitative Rulesmentioning

confidence: 99%

“…j denotes a threshold value for the input X i . Rule extraction techniques for recurrent networks are described in Das and Das (1991), Giles and Omlin (1993), and more recently in Vahed and Omlin (1999). D'Avila Garcez et al (2001) present a sound extraction algorithm for multilayer feedforward networks with discrete inputs and one hidden layer.…”

mentioning

confidence: 99%

From Neural Networks to Qualitative Models in Environmental Engineering

Wieland

Wotawa

Wotawa³

2002

Computer aided Civil Eng

View full text Add to dashboard Cite

As an alternative to physical models, artificial neural networks (ANNs) are a valuable forecast tool in environmental sciences. They can be used effectively due to their learning capabilities and their low computational costs. Once all relevant variables of the system are identified and put into the network, it works quickly and accurately. However, one of the major shortcomings of neural networks is that they do not reveal causal relationships between major system components and thus are unable to improve the explicit knowledge of the user. Another problem is due to the fact that reasoning is only done from the inputs to the outputs. In cases where the opposite is requested (i.e., deriving inputs leading to a given output), neural networks can hardly be used. To overcome these problems, we introduce a novel approach for deriving qualitative information out of neural networks. Some of the resulting rules can directly be used by a qualitative simulator for producing possible future scenarios. Because of the explicit representation of knowledge, the rules should be easier to understand and can be used as a starting point for creating models wherever a physical model is not available.Moreover, the resulting rules are well adapted to be used in decision support systems. We illustrate our approach by introducing a network for predicting surface ozone concentrations and show how rules can be derived from the network and how the approach can be naturally extended for use in decision support systems.

show abstract

Rule extraction from recurrent neural networks using a symbolic machine learning algorithm

Cited by 14 publications

References 17 publications

Data Mining with Computational Intelligence

Data Mining with Computational Intelligence

Neuro-fuzzy rule generation: survey in soft computing framework

From Neural Networks to Qualitative Models in Environmental Engineering

Contact Info

Product

Resources

About