Quantifying the separability of data classes in neural networks

DOI10.1016/J.NEUNET.2021.03.035MaRDI QIDQ6054550zbMATH OpenOpenAlexFDO

Authors

Publication date 28 September 2023

Published in Neural Networks (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Full work available at URL https://doi.org/10.1016/j.neunet.2021.03.035

zbMATH Keywords

data class separabilitydeep learning interpretabilitydiscrimination valueneural architecture searchneural network analysisrepresentational similarity analysis

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Neural biology (92C20)

Recommendations

• Estimates of Data Complexity in Neural-Network Learning
• Generalization from correlated sets of patterns in the perceptron
• scientific article; zbMATH DE number 1203217
• On the realization of discriminant functions by means of multilayer perceptrons
• scientific article; zbMATH DE number 759415

Cites work

• Deep convolutional neural networks for image classification: a comprehensive review
• Graph clustering
• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• scientific article; zbMATH DE number 5286897 (Why is no real title available?)
• scientific article; zbMATH DE number 2080487 (Why is no real title available?)
• Multidimensional scaling. I: Theory and method
• Networks
• Neural architecture search: a survey
• Nonmetric multidimensional scaling. A numerical method
• Scikit-learn: machine learning in Python
• Visualizing data using t-SNE
• Why does deep and cheap learning work so well?

Cited in

(1)

• Quantifying overfitting in deep learning

This page was built for publication: Quantifying the separability of data classes in neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6054550)