Use of some sensitivity criteria for choosing networks with good generalization ability

By Yannis Dimopoulos, P. Bourret, Sovan Lek. 1995

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

Explaining Recurrent Neural Network Predictions in Sentiment Analysis (2017, background): “We refer to the above definition of relevance as Sensitivity Analysis (SA) (Dimopoulos et al., 1995; Gevrey et al., 2003).”
Explaining Predictions of Non-Linear Classifiers in NLP (2016, background): “An alternative procedure called sensitivity analysis (SA) produces explanations by scoring input variables based on how they affect the decision output locally (Dimopoulos et al., 1995; Gevrey et al., 2003).”
Explaining Therapy Predictions with Layer-Wise Relevance Propagation in Neural Networks (2018, methodology): “A closely related method is sensitivity analysis [33], which calculates the partial derivative of each feature”
Human-grounded Evaluations of Explanation Methods for Text Classification (2019, methodology): “, 2016), gradient analysis (Dimopoulos et al., 1995), and relevance propagation (Arras et al.”
The Future of Sensitivity Analysis: An essential discipline for systems modeling and policy support (2020, unknown): “…SA (e.g., Lek et al., 1995; 1996; Maier and Dandy, 1997; Liong et al., 2000) and the calculation of partial derivatives of the model outputs in response to changes in the model inputs (e.g. Dimopoulos et al., 1995; 1999; Tison et al., 2007; Vasilakos et al., 2009; Mount et al., 2013).”
The use of artificial neural networks to analyze and predict alongshore sediment transport (2010, methodology): “The larger the value of SSDi , the more influence input variablexi has on the output.”
Machine Learning Methods Without Tears: A Primer for Ecologists (2008, methodology): “Other approaches include Garson’s algorithm (Garson 1991), partial derivatives (Dimopoulos et al. 1995), a sensitivity analysis to determine the spectrum of input variable contributions in the neural network (Lek et al. 1996), and a number of pruning algorithms (Bishop 1995), including a…”
Bond Risk Premia with Machine Learning∗ (2018, unknown): “These partial derivatives represent the sensitivity of the output to the ith input, conditional on the network structure and the average value of the other input variables (see Dimopoulos et al., 1995), and are akin to the betas of a simple linear regression.”
Review of soft sensor methods for regression applications (2016, unknown): “the output with respect to that variable [76; 77].”
An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data (2004, methodology): “Computes the partial derivatives of the ANN output with respect to the input neurons (see Dimopoulos et al., 1995, 1999).”
Empirical Asset Pricing via Machine Learning (2018, unknown): “Our portfolio construction differs slightly from the actual S&P 500 index and the characteristic-based Fama-French portfolios (Fama and French 1993, 2015), but has the virtue that we can exactly track the ex ante portfolio weights of each.38 Table 5 reports the monthly out-of-sample R2 over our 30-y”