This research demonstrates the efficacy of neural network operators in approximating non-negative functions, suggesting broad applications in function estimation.
In this work we study the univariate and multivariate quantitative approximation by multi-composite Kantorovich–Choquet-type quasi-interpolation neural network operators with respect to the supremum norm. This is achieved with rates via the first univariate and multivariate moduli of continuity. We approximate continuous and bounded non-negative functions on RN,N∈N. When they are also uniformly continuous we have pointwise and uniform convergences, plus Lp estimates. Our multi-composite activation functions are formed by general sigmoid functions.
No takes yet. Share an insight, caveat, or question.
George A. Anastassiou (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: