Levenberg-Marquardt multi-classification using hinge loss function

DOI10.1016/J.NEUNET.2021.07.010MaRDI QIDQ6055118zbMATH OpenOpenAlexFDO

Authors Buse Melis Ozyildirim, Mariam Kiran

Publication date 28 September 2023

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2021.07.010

zbMATH Keywords

classificationhinge lossLevenberg-Marquardtloss functionsneural networks

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07)

Recommendations

• On the Relation Between Loss Functions and T-Norms
• Power function error initialization can improve convergence of backpropagation learning in neural networks for classification
• Optimization methods for large-scale machine learning
• Optimization for deep learning: an overview
• Online primal-dual learning for a data-dependent multi-kernel combination model with multiclass visual categorization applications

Cites work

• A linear functional strategy for regularized ranking
• A perfect example for the BFGS method
• A three-parameter family of nonlinear conjugate gradient methods
• Are Loss Functions All the Same?
• scientific article; zbMATH DE number 1573291 (Why is no real title available?)
• Neural networks and deep learning. A textbook
• Regularization techniques and suboptimal solutions to optimization problems in learning from data
• Some thoughts about the design of loss functions
• Statistical decision theory and Bayesian analysis. 2nd ed
• The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
• The use of monotonicity for choosing the regularization parameter in ill-posed problems

Cited in

(5)

• scientific article; zbMATH DE number 5251636 (Why is no real title available?)
• A novel multi-scale loss function for classification problems in machine learning
• Advancing neural network calibration: the role of gradient decay in large-margin Softmax optimization
• An error analysis for deep binary classification with sigmoid loss
• Enhancing deep learning algorithm accuracy and stability using multicriteria optimization: an application to distributed learning with MNIST digits

This page was built for publication: Levenberg-Marquardt multi-classification using hinge loss function

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6055118)