Neural network training and rule extraction with augmented discretized input
College
College of Computer Studies
Department/Unit
Software Technology
Document Type
Article
Source Title
Neurocomputing
Volume
207
First Page
610
Last Page
622
Publication Date
9-26-2016
Abstract
© 2016 Elsevier B.V. The classification and prediction 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 dividing the original interval of each continuous attribute into subintervals of equal length. 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 comprehensible classification rules can be extracted from the pruned network by analyzing the activations of the network hidden units and the weights of the network connections that remain in the pruned network. Our experiments on artificial data sets show that the rules extracted from the neural networks can perfectly replicate the class membership rules used to create the data perfectly. On real-life benchmark data sets, neural networks trained with augmented discretized inputs are shown to achieve better accuracy than neural networks trained with the original data.
html
Digitial Object Identifier (DOI)
10.1016/j.neucom.2016.05.040
Recommended Citation
Hayashi, Y., Setiono, R., & Azcarraga, A. P. (2016). Neural network training and rule extraction with augmented discretized input. Neurocomputing, 207, 610-622. https://doi.org/10.1016/j.neucom.2016.05.040
Upload File
wf_no