How to determine the unique contributions of input-variables to the nonlinear regression function of a multilayer perceptron
There are different methods for quantifying the relative contribution of input-variables to the nonlinear regression function provided by a Multilayer Perceptron. Unfortunately most of the systematic method comparisons available to date suffer from a set of characteristic shortcomings. This paper el...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
15 May 2015
|
| In: |
Ecological modelling
Year: 2015, Volume: 309-310, Pages: 60-63 |
| ISSN: | 0304-3800 |
| DOI: | 10.1016/j.ecolmodel.2015.04.015 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1016/j.ecolmodel.2015.04.015 Verlag, lizenzpflichtig, Volltext: https://www.sciencedirect.com/science/article/pii/S0304380015001660 
|
| Author Notes: | Andreas Fischer |
| Summary: | There are different methods for quantifying the relative contribution of input-variables to the nonlinear regression function provided by a Multilayer Perceptron. Unfortunately most of the systematic method comparisons available to date suffer from a set of characteristic shortcomings. This paper elaborates on these methodological shortcomings and presents a simulation study that demonstrates how to avoid them in future method comparisons. Results of the simulation study indicate that Garson's weight method is preferable to the connection weight method proposed by Olden et al., (2004) for each of the samples simulated. |
|---|---|
| Item Description: | Gesehen am 03.08.2021 |
| Physical Description: | Online Resource |
| ISSN: | 0304-3800 |
| DOI: | 10.1016/j.ecolmodel.2015.04.015 |