Probabilistic Bounds for Binary Classification of Large Data Sets

0503127 - ÚI 2021 RIV CH eng C - Conference Paper (international conference)
Kůrková, Věra - Sanguineti, M.
Probabilistic Bounds for Binary Classification of Large Data Sets.
Recent Advances in Big Data and Deep Learning. Cham: Springer, 2020 - (Oneto, L.; Navarin, N.; Sperduti, A.; Anguita, D.), s. 309-319. Proceedings of the International Neural Networks Society, 1. ISBN 978-3-030-16840-7. ISSN 2661-8141.
[INNSBDDL 2019: INNS Big Data and Deep Learning /4./. Sestri Levante (IT), 16.04.2019-18.04.2019]
R&D Projects: GA ČR(CZ) GA18-23827S
Institutional support: RVO:67985807
Keywords : Binary classification * Approximation by feedforward networks * Concentration of measure * Azuma-Hoeffding inequality
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

A probabilistic model for classification of task relevance is investigated. Correlations between randomly-chosen functions and network input-output functions are estimated. Impact of large data sets is analyzed from the point of view of the concentration of measure phenomenon. The Azuma-Hoeffding Inequality is exploited, which can be applied also when the naive Bayes assumption is not satisfied (i.e., when assignments of class labels to feature vectors are not independent).
Permanent Link: http://hdl.handle.net/11104/0294978