Sensitivity Analysis for Decision Boundaries |
| |
Authors: | Engelbrecht AP |
| |
Affiliation: | (1) Department of Computer Science, University of Pretoria, Pretoria, South Africa, e-mail |
| |
Abstract: | A novel approach is presented to visualize and analyze decision boundaries for feedforward neural networks. First order sensitivity analysis of the neural network output function with respect to input perturbations is used to visualize the position of decision boundaries over input space. Similarly, sensitivity analysis of each hidden unit activation function reveals which boundary is implemented by which hidden unit. The paper shows how these sensitivity analysis models can be used to better understand the data being modelled, and to visually identify irrelevant input and hidden units. |
| |
Keywords: | sensitivity analysis decision boundary feedforward neural network feature extraction pruning irrelevant parameters |
本文献已被 SpringerLink 等数据库收录! |
|