A new method for explaining neural network reasoning

This paper presents a new method for explaining the reasoning results of a trained neural network. The method considers the most significant attribute first under the guidance of a relative strength of effect analysis and eliminates irrelevant points. Following the adaptive search in the dynamic state space, a set of relevant points are extracted and form the basis of the explanation of the neural network reasoning. Combining a relative strength of effect analysis with the relevant points, a case based explanation approach is put forward. As an illustration, an experiment with a small data set on the relationship between weather conditions and play decisions is presented to demonstrate the utility of the proposed approach.

[1]  G. P. Fletcher,et al.  Using neural networks as a tool for constructing rule based systems , 1995, Knowl. Based Syst..

[2]  Jude Shavlik,et al.  THE EXTRACTION OF REFINED RULES FROM KNOWLEDGE BASED NEURAL NETWORKS , 1993 .

[3]  Huan Liu,et al.  NeuroLinear: From neural networks to oblique decision rules , 1997, Neurocomputing.

[4]  Karuna Pande Joshi,et al.  Analysis of Data Mining Algorithms , 1997 .

[5]  T. J. Cholewo,et al.  Crisp Rule Extraction from Perceptron Network Classifiers , 1996 .

[6]  G. P. Fletcher,et al.  Producing evidence for the hypotheses of large neural networks , 1996, Neurocomputing.

[7]  Joachim Diederich,et al.  The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks , 1998, IEEE Trans. Neural Networks.

[8]  Chris J. Hinde,et al.  A new method to evaluate a trained artificial neural network , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[9]  Jacek M. Zurada,et al.  Extraction of rules from artificial neural networks for nonlinear regression , 2002, IEEE Trans. Neural Networks.

[10]  Joachim Diederich,et al.  Survey and critique of techniques for extracting rules from trained artificial neural networks , 1995, Knowl. Based Syst..

[11]  Włodzisław Duch,et al.  Extraction of logical rules from training data using backpropagation networks , 2000 .

[12]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[13]  Ronald J. Patton,et al.  Interpretation of Trained Neural Networks by Rule Extraction , 2001, Fuzzy Days.