Abstract
Neural networks are well-known for their powerful capability in producing high prediction accuracy. However, due to the non-linear calculations in the network, it is very difficult for users to understand which input features are important in leading to final predictions. In this study, we propose a two-step pipeline approach that uses two sets of linear models to estimates feature importance in the input dataset X that leads to the class prediction specified in Y. More specifically, the first linear regression model derives the feature importance in X in explaining the Z-code that was extracted from any hidden layer of a trained neural network. The second linear classification model captures the importance in the Z- code in predicting the target class Y. We then combine the first X to Z importance with the second Z to Y importance together to approximate the non-linear importance from X to Y. The experiments conducted in this study also show that our method is sound and stable in selecting the truly important features from input datasets regardless how a neural network was constructed with different parameters such as activation functions or the number of hidden layers.
Original language | English (US) |
---|---|
Title of host publication | 2019 14th Annual Conference System of Systems Engineering, SoSE 2019 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 25-30 |
Number of pages | 6 |
ISBN (Electronic) | 9781728104577 |
DOIs | |
State | Published - May 2019 |
Event | 14th Annual Conference System of Systems Engineering, SoSE 2019 - Anchorage, United States Duration: May 19 2019 → May 22 2019 |
Publication series
Name | 2019 14th Annual Conference System of Systems Engineering, SoSE 2019 |
---|
Conference
Conference | 14th Annual Conference System of Systems Engineering, SoSE 2019 |
---|---|
Country/Territory | United States |
City | Anchorage |
Period | 5/19/19 → 5/22/19 |
Bibliographical note
Publisher Copyright:© 2019 IEEE.
Keywords
- Autoencoder
- Hidden layer
- Linear regression
- Logistic regression
- Neural network