𝔖 Bobbio Scriptorium
✦   LIBER   ✦

A unified approach for neural network-like approximation of non-linear functionals

✍ Scribed by Tianping Chen

Publisher
Elsevier Science
Year
1998
Tongue
English
Weight
56 KB
Volume
11
Category
Article
ISSN
0893-6080

No coin nor oath required. For personal study only.

✦ Synopsis

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.

πŸ“œ SIMILAR VOLUMES

Dissipativity as a unified approach to s
Dissipativity as a unified approach to sandberg-willson-type properties of non-linear transistor networks
✍ Corneliu A. Marinov πŸ“‚ Article πŸ“… 1990 πŸ› John Wiley and Sons 🌐 English βš– 966 KB

A class of circuits is considered consisting of semiconductor devices (non-linearly modelled bipolar transistors and junction diodes), non-linear capacitors and inductors, all connected to a non-linear resistive multiport. This multiport is described by a global piecewise continuously differentiable

A unified treatment of superconvergent r
A unified treatment of superconvergent recovered gradient functions for piecewise linear finite element approximations
✍ G. Goodsell; J. R. Whiteman πŸ“‚ Article πŸ“… 1989 πŸ› John Wiley and Sons 🌐 English βš– 523 KB

Piecewise linear finite element approximations to two-dimensional Poisson problems are treated. For simplicity, consideration is restricted to problems having Dirichlet boundary conditions and defined on rectangular domains R which are partitioned by a uniform triangular mesh. It is also required th