Enhancing deep learning algorithm accuracy and stability using multicriteria optimization: an application to distributed learning with MNIST digits

DOI10.1007/S10479-022-04833-XMaRDI QIDQ6589086FDOQ6589086

Authors: Davide La Torre, Danilo Liuzzi, Matteo Rocca 

Publication date: 19 August 2024

Published in: Annals of Operations Research (Search for Journal in Brave)

Recommendations

• A novel multi-scale loss function for classification problems in machine learning
• Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences
• Optimization methods for large-scale machine learning
• Levenberg-Marquardt multi-classification using hinge loss function
• Application of Monte Carlo stochastic optimization (MOST) to deep learning

zbMATH Keywords

classificationdeep learningmachine learningartificial intelligencemulticriteria optimizationMINST data

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Mathematical programming (90Cxx) Computer science (68-XX)

Cites Work

• Title not available (Why is that?)
• Deep learning
• Understanding machine learning. From theory to algorithms
• Theory of multiobjective optimization
• A logical calculus of the ideas immanent in nervous activity
• Sufficient conditions of isolated minimizers for constrained programming problems
• Machine learning. The art and science of algorithms that make sense of data.
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Galerkin method for constrained variational equations and a collage-based approach to related inverse problems
• Title not available (Why is that?)
• Mathematics for Machine Learning
• Title not available (Why is that?)
• Algorithmic aspects of machine learning
• Solving inverse problems for steady-state equations using a multiple criteria model with collage distance, entropy, and sparsity
• MODEL THEORY AND MACHINE LEARNING
• Machine Learning Fundamentals
• A multi-criteria approach to evolve sparse neural architectures for stock market forecasting

Cited In (1)

• Enhancing deep stochastic configuration networks: efficient training via low-rank matrix approximation

This page was built for publication: Enhancing deep learning algorithm accuracy and stability using multicriteria optimization: an application to distributed learning with MNIST digits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6589086)