𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Some new results on neural network approximation

✍ Scribed by K. Hornik

Publisher
Elsevier Science
Year
1993
Tongue
English
Weight
346 KB
Volume
6
Category
Article
ISSN
0893-6080

No coin nor oath required. For personal study only.

✦ Synopsis

We show that standardfeedforward networks with asl ew as a single hidden layer can uniformly approximate continuousfunctions on compacta provided that the activation function if; is locally R iemann integrable and nonpolynomial, and have universal LP(Jl) approximation capabilities for finite and compactly supportedinput environment measures JL provided that if; is locall y boundedand nonpolyn om ial. In both cases, the input-to-hidden weights and hidden layer biases can be constrained to arbitraril y small sets; if in addition if; is locally analytic a single universalbias will do.

πŸ“œ SIMILAR VOLUMES

Universal Approximation Using Feedforwar
Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results
✍ Franco Scarselli; Ah Chung Tsoi πŸ“‚ Article πŸ“… 1998 πŸ› Elsevier Science 🌐 English βš– 699 KB

In this paper, we present a review of some recent works on approximation by feedforward neural networks. A particular emphasis is placed on the computational aspects of the problem, i.e. we discuss the possibility of realizing a feedforward neural network which achieves a prescribed degree of accura

New study on neural networks: the essent
New study on neural networks: the essential order of approximation
✍ Jianjun Wang; Zongben Xu πŸ“‚ Article πŸ“… 2010 πŸ› Elsevier Science 🌐 English βš– 374 KB

For the nearly exponential type of feedforward neural networks (neFNNs), the essential order of their approximation is revealed. It is proven that for any continuous function defined on a compact set of R(d), there exist three layers of neFNNs with the fixed number of hidden neurons that attain the