Quo Vadis? Reliable and Practical Rule Extraction from Neural Networks
Data(s) |
2010
|
---|---|
Resumo |
Rule extraction from neural network algorithms have been investigated for two decades and there have been significant applications. Despite this level of success, rule extraction from neural network methods are generally not part of data mining tools, and a significant commercial breakthrough may still be some time away. This paper briefly reviews the state-of-the-art and points to some of the obstacles, namely a lack of evaluation techniques in experiments and larger benchmark data sets. A significant new development is the view that rule extraction from neural networks is an interactive process which actively involves the user. This leads to the application of assessment and evaluation techniques from information retrieval which may lead to a range of new methods. |
Identificador | |
Publicador |
Springer |
Relação |
DOI:10.1007/978-3-642-05177-7_24 Diederich, Joachim, Tickle, Alan B., & Geva, Shlomo (2010) Quo Vadis? Reliable and Practical Rule Extraction from Neural Networks. In Advances in Machine Learning I. Springer, Berlin ; Heidelberg, pp. 479-490. |
Fonte |
Faculty of Science and Technology; Institute for Future Environments |
Tipo |
Book Chapter |