Feature Salience for Neural Networks: Comparing Algorithms
One of the key problems in the field of telemedicine is the prediction of the patient’s health state change based on incoming non-invasively measured vital data. Artificial Neural Networks (ANN) are a powerful statistical modeling tool suitable for this problem. Feature salience algorithms for ANN provide information about feature importance and help selecting relevant input variables. Looking for a reliable salience analysis algorithm, we found a relatively wide range of possible approaches. However, we have also found numerous methodological weaknesses in corresponding evaluations. Perturb  and Connection Weight (CW)  are two of the most promising algorithms. In this paper, we propose an improvement for Connection Weight and evaluate it along with Perturb and the original CW. We use three independent datasets with already known feature salience rankings as well as varying topologies and random feature ranking results to estimate the usability of the tested approaches for feature salience assessment in complex multi-layer perceptrons.
KeywordsFeature Salience Sensitivity Analysis Neural Networks Machine Learning Telemedicine
Unable to display preview. Download preview PDF.
- 7.Bai, R., Jia, H., Cao, P.: Factor Sensitivity Analysis with Neural Network Simulation based on Perturbation System. Journal of Computers 6 (2011)Google Scholar
- 8.Garson, G.D.: Interpreting neural-network connection weights. AI Expert 6, 46–51 (1991)Google Scholar
- 14.Prechelt, L.: Proben 1. Presented at the Technical Report 21/94 (1994)Google Scholar
- 15.Riedmiller, M., Braun, H.: RPROP - A Fast Adaptive Learning Algorithm. In: Proc. of ISCIS VII, Universitat (1992)Google Scholar
- 16.Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors, vol. 323, pp. 533–536 (1986) (published online: October 09, 1986), doi:10.1038/323533a0Google Scholar
- 17.Heinze, T., von Lowis, M., Polze, A.: Joint multi-frame demosaicing and super-resolution with artificial neural networks. In: 2012 19th International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 540–543 (2012)Google Scholar
- 19.UCI Machine Learning Repository, http://archive.ics.uci.edu/ml/datasets.html