Developing an empirical model of phytoplankton primary production: a neural network case study

By M. Scardi, L. Harding. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

All Models are Wrong, but Many are Useful: Learning a Variable’s Importance by Studying an Entire Class of Prediction Models Simultaneously (2018, methodology): “A similar “Perturb” VI measure has been used for neural networks, where noise is added to covariates (Recknagel et al., 1997; Yao et al., 1998; Scardi and Harding, 1999; Gevrey et al., 2003).”
Opening the black box - data driven visualization of neural networks (2005, methodology): “Scardi and Harding [24] modify only one of the input variables at a time and the corresponding output is used to determine the in uence of each input variable.”
An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data (2004, background): “The resulting change in mean square error for each Input Perturbation illustrates the relative importance of the predictor variables (see Scardi and Harding, 1999 ).”
Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks (2002, background): “Scardi and Harding (1999) added white noise to each input variable and examined the resulting changes in the mean square error of the output.”
Predicting the species richness of aquatic insects in streams using a limited number of environmental variables (2003, methodology): “A sensitivity analysis (i.e., a method to study the behavior of a model; Scardi and Harding 1999) was conducted to determine the contribution of each input variable to the values of the output variable of the model.”
Neural network and genetic programming for modelling coastal algal blooms (2006, methodology): “Although most of these studies are applied to freshwater environments (i.e., limnological or riverine systems), a few have been applied to saltwater eutrophic areas (Scardi and Harding, 1999; Scardi, 2001; Lee et al., 2003; Muttil et al., 2004).”
All Models are Wrong but many are Useful: Variable Importance for Black-Box, Proprietary, or Misspecified Prediction Models, using Model Class Reliance (2018, methodology): “015; Datta et al., 2016; Gregorutti et al., 2017). A similar \Perturb" VI measure has been used for neural networks, where noise is added to covariates (Recknagel et al., 1997; Yao et al., 1998; Scardi and Harding, 1999; Gevrey et al., 2003). Such tools can be useful for identifying covariates ”
Review and comparison of methods to study the contribution of variables in artificial neural network models (2003, methodology): “In fact, the mean square error (MSE) of the neural network output is expected to increase as a larger amount of noise is added to the selected input variable (Yao et al., 1998; Scardi and Harding, 1999 ).”