MofN rule extraction from neural networks trained with augmented discretized input
College
College of Computer Studies
Department/Unit
Software Technology
Document Type
Conference Proceeding
Source Title
Proceedings of the International Joint Conference on Neural Networks
First Page
1079
Last Page
1086
Publication Date
1-1-2014
Abstract
The accuracy of neural networks can be improved when they are trained with discretized continuous attributes as additional inputs. Such input augmentation makes it easier for the network weights to form more accurate decision boundaries when the data samples of different classes in the data set are contained in distinct hyper-rectangular subregions in the original input space. In this paper we present first how a neural network can be trained with augmented discretized inputs. The additional inputs are obtained by simply dividing the original interval of each continuous attribute into subintervals of equal length. Thermometer encoding scheme is used to represent these discretized inputs. The network is then pruned to remove most of the discretized inputs as well as the original continuous attributes as long as the network still achieves a minimum preset accuracy requirement. We then discuss how MofN rules can be extracted from the pruned network by analyzing the activations of the network's hidden units and the weights of the network connections that remain in the pruned network. For data sets that have sample classes defined by relatively complex boundaries, surprisingly simple MofN rules with very good accuracy rates are obtained. © 2014 IEEE.
html
Digitial Object Identifier (DOI)
10.1109/IJCNN.2014.6889691
Recommended Citation
Setiono, R., Azcarraga, A. P., & Hayashi, Y. (2014). MofN rule extraction from neural networks trained with augmented discretized input. Proceedings of the International Joint Conference on Neural Networks, 1079-1086. https://doi.org/10.1109/IJCNN.2014.6889691
Disciplines
Computer Sciences
Keywords
Neural networks (Computer science); Data sets
Upload File
wf_no