(Enter summary)
Abstract: Although backpropagation neural networks
generally predict better than decision trees do
for pattern classification problems, they are often
regarded as black boxes, i.e., their predictions
are not as interpretable as those of decision
trees. This paper argues that this is because
there has been no proper technique that
enables us to do so. With an algorithm that
can extract rules
1
, by drawing parallels with
those of decision trees, we show that the predictions
of a network can be ... (Update)
Context of citations to this paper: More
...to determine exactly how the neural network is making its decision. Techniques have been proposed to extract rules from neural networks [53], but these rules are not always accurate. Perceptrons do not suffer from this opaqueness; the perceptron s decision making process is...
Cited by: More
Computational Intelligence Methods for Rule-Based Data.. - Duch, Setiono, Zurada (2004)
(Correct)
Quantum Computation and Natural Language Processing - Chen (2002)
(Correct)
Neural Methods for Dynamic - Branch Prediction Daniel
(Correct)
Similar documents (at the sentence level):
60.8%: Symbolic Representation of Neural Networks - Setiono, Liu (1996)
(Correct)
Active bibliography (related documents): More All
0.1: NeuroLinear: From neural networks to oblique decision rules - Setiono, Liu (1997)
(Correct)
0.1: NeuroRule: A Connectionist Approach to Data Mining - Lu (1995)
(Correct)
0.1: Evolutionary Design of Neural Networks for Classification.. - Rocha, Cortez, Neves (2005)
(Correct)
Similar documents based on text: More All
0.1: Neural-Network Feature Selector - Setiono, Liu (1997)
(Correct)
0.1: Fragmentation Problem and Automated Feature Construction - Rudy Setiono And
(Correct)
0.1: Effective Data Mining Using Neural Networks - Lu, Setiono, Liu (1996)
(Correct)
Related documents from co-citation: More All
8: Induction of Decision Trees (context) - Quinlan - 1986
8: Programs for machine learning (context) - Quinlan - 1993
8: A survey and critique of techniques for extracting rules from trained artificial.. (context) - Andrews, Diederich et al. - 1995
BibTeX entry: (Update)
Setiono, R. & Liu, H. (1995). Understanding neural networks via rule extraction. In Proc. of the 14th International Joint Conference on Artificial Intelligence, (pp. 480--485), Montreal, Canada. http://citeseer.ist.psu.edu/setiono95understanding.html More
@inproceedings{ setiono95understanding,
author = "Rudy Setiono and Huan Liu",
title = "Understanding Neural Networks via Rule Extraction",
booktitle = "{IJCAI}",
pages = "480-487",
year = "1995",
url = "citeseer.ist.psu.edu/setiono95understanding.html" }
Citations (may not include all citations):
2177
Programs for Machine Learning (context) - Quinlan - 1993
231
The use of multiple measurements in taxonomic problems (context) - Fisher - 1936
111
Extracting refined rules from knowledge-based neural network..
- Towell, Shavlik - 1993 ACM DBLP
85
Chimerge: Discretization of numeric attributes (context) - Kerber - 1992 DBLP
55
Symbolic and neural learning algorithms: An experimental com.. (context) - Shavlik, Mooney et al. - 1991 DBLP
54
Neural Networks in Computer Intelligence (context) - Fu - 1994 ACM
44
Training knowledge-based neural networks to recognize genes ..
- Noordewieer, Towell et al. - 1991 ACM
34
Medical diagnostic expert system based on pdp model (context) - Saito, Nakano - 1988
33
Comparing connectionist and symbolic learning methods
- Quinlan - 1994 ACM
26
Neural networks for Statistical Modeling (context) - Smith - 1993 ACM
22
A penalty function approach for pruning feedforward neural n..
- Setiono - 1995
21
Improved decision trees: A generalized version of id (context) - Cheng, Fayyad et al. - 1988
18
A comparative study of id3 and backpropagation for english t..
- Dietterich, Hild et al. - 1990 ACM DBLP
2
Department of Info Sys and Comp Sci (context) - Liu, rules - 1995
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.comp.nus.edu.sg/~liuh/publications.html): More
Towards an Evolutionary Algorithm: A Comparison of Two Feature.. - Chen, Liu
(Correct)
A Family of Efficient Rule Generators - Liu
(Correct)
Joint Concept Formation - Liu, Wen
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC