6533b7d4fe1ef96bd1262785

RESEARCH PRODUCT

Weight Adaptation Stability of Linear and Higher-Order Neural Units for Prediction Applications

Edgar A. Martinez-garciaRicardo Rodríguez-jorgeJiri BilaJolanta Mizera-pietraszko

subject

Dynamic modelsComputer scienceOrder (business)Control theoryStability (learning theory)Verifiable secret sharingAdaptation (computer science)Gradient descent

description

This paper is focused on weight adaptation stability analysis of static and dynamic neural units for prediction applications. The aim of this paper is to provide verifiable conditions in which the weight system is stable during sample-by-sample adaptation. The paper presents a novel approach toward stability of linear and higher-order neural units. A study of utilization of linear and higher-order neural units with the foundations on stability of the gradient descent algorithm for static and dynamic models is addressed.

yearjournalcountryeditionlanguage
2018-08-15
https://doi.org/10.1007/978-3-319-98678-4_50