A unified approach for neural network-like approximation of non-linear functionals.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 12662768.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
In this paper, we give a universal approach to approximation of non-linear functionals and so called myopic input-output maps by neural network-like architectures. Strong theorems on equi-uniform approximation to functionals in abstract spaces are given. As applications, theorems on identification of non-linear systems, whose inputs belong to compact sets in C(R(q),R(p)), are given. It is pointed out that: (1) the weighted approximation can be reduced to non-weighted approximation; (2) the continuous case and discrete case can be dealt with universally.