An upper bound on the variance of scalar multilayer perceptrons for log-concave distributions
Authors:
- Aydin SarrafASAydin Sarraf
- Saeed KhaliliSKSaeed Khalili
- 1 June 2022
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 488, 540-546
Abstract
No abstract availableKeywords
This publication has 28 references indexed in Scilit:
- Weighted Poincaré-type inequalities for Cauchy and other convex measuresThe Annals of Probability, 2009
- Numeric sensitivity analysis applied to feedforward neural networksNeural Computing and Applications, 2003
- Sensitivity analysis of multilayer perceptron to input and weight perturbationsIEEE Transactions on Neural Networks, 2001
- Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimatesMathematics and Computers in Simulation, 2001
- Bagging for linear classifiersPattern Recognition, 1998
- Poincaré’s inequalities and Talagrand’s concentration phenomenon for the exponential distributionProbability Theory and Related Fields, 1997
- A note on variance reductionStatistics & Probability Letters, 1995
- Sensitivity analysis of multilayer perceptron with differentiable activation functionsIEEE Transactions on Neural Networks, 1992
- Sensitivity of feedforward neural networks to weight errorsIEEE Transactions on Neural Networks, 1990
- On extensions of the Brunn-Minkowski and Prékopa-Leindler theorems, including inequalities for log concave functions, and with an application to the diffusion equationJournal of Functional Analysis, 1976