Two-layer neural networks with values in a Banach space
From MaRDI portal
Publication:6366901
Artificial neural networks and deep learning (68T07) Computational learning theory (68Q32) Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Spaces of vector- and operator-valued functions (46E40) Numerical solution to inverse problems in abstract spaces (65J22)
Abstract: We study two-layer neural networks whose domain and range are Banach spaces with separable preduals. In addition, we assume that the image space is equipped with a partial order, i.e. it is a Riesz space. As the nonlinearity we choose the lattice operation of taking the positive part; in case of -valued neural networks this corresponds to the ReLU activation function. We prove inverse and direct approximation theorems with Monte-Carlo rates for a certain class of functions, extending existing results for the finite-dimensional case. In the second part of the paper, we study, from the regularisation theory viewpoint, the problem of finding optimal representations of such functions via signed measures on a latent space from a finite number of noisy observations. We discuss regularity conditions known as source conditions and obtain convergence rates in a Bregman distance for the representing measure in the regime when both the noise level goes to zero and the number of samples goes to infinity at appropriate rates.
This page was built for publication: Two-layer neural networks with values in a Banach space
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6366901)
