On the Relation Between Loss Functions and T-Norms

DOI10.1007/978-3-030-49210-6_4MaRDI QIDQ5041765zbMATH OpenOpenAlexFDO

Authors Francesco Giannini, Giuseppe Marra, Marco Gori, M. Diligenti, Marco Maggini

Publication date 14 October 2022

Published in Inductive Logic Programming (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1907.07904

zbMATH Keywords

learning from constraintsloss functionst-norms

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07) Reasoning under uncertainty in the context of artificial intelligence (68T37)

Recommendations

• scientific article; zbMATH DE number 2080657
• Loss functions for loss estimation
• Some thoughts about the design of loss functions
• Loss functions
• scientific article; zbMATH DE number 4104245
• An investigation for loss functions widely used in machine learning
• On Spiring's normal loss function
• Loss functions, complexities, and the Legendre transformation.

Cites work

• A note on the ordinal sum theorem and its consequence for the construction of triangular norms
• Absorbent tuples of aggregation operators
• Aggregation functions: means
• Deep learning
• Fuzzy measures and integrals in evaluation of strategies
• Hinge-loss Markov random fields and probabilistic soft logic
• scientific article; zbMATH DE number 5296741 (Why is no real title available?)
• scientific article; zbMATH DE number 1354791 (Why is no real title available?)
• scientific article; zbMATH DE number 1986059 (Why is no real title available?)
• Markov logic networks
• Metamathematics of fuzzy logic
• Semantic-based regularization for learning and inference
• Triangular norms
• Triangular norms. Position paper I: Basic analytical and algebraic properties.
• Triangular norms. Position paper II: General constructions and parameterized families
• Triangular norms. Position paper III: Continuous t-norms

Cited in

(7)

• A new perspective on the normalization of invariant measures for loss networks on other product form systems.
• Interpreting the basis path set in neural networks
• scientific article; zbMATH DE number 2080657 (Why is no real title available?)
• On Spiring's normal loss function
• Power function error initialization can improve convergence of backpropagation learning in neural networks for classification
• Levenberg-Marquardt multi-classification using hinge loss function
• Magnitude and angle dynamics in training single ReLU neurons

This page was built for publication: On the Relation Between Loss Functions and T-Norms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5041765)