Quantitative self adjoint operator other direct approximations
Abstract
Here we give a series of self adjoint operator positive linear operators general results. Then we present specific similar results related to neural networks. This is a quantitative treatment to determine the degree of self adjoint operator uniform approximation with rates, of sequences of self adjoint positive linear operators in general, and in particular of self adjoint specific neural network operators. The approach is direct relying on Gelfand’s isometry. It follows [4] (Anastassiou, J. Nonlinear Sci. Appl. (2016)).
Publication Title
Studies in Computational Intelligence
Recommended Citation
Anastassiou, G. (2017). Quantitative self adjoint operator other direct approximations. Studies in Computational Intelligence, 699, 47-60. https://doi.org/10.1007/978-3-319-51475-8_3
