๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Random Approximants and Neural Networks

โœ Scribed by Y. Makovoz

Publisher
Elsevier Science
Year
1996
Tongue
English
Weight
492 KB
Volume
85
Category
Article
ISSN
0021-9045

No coin nor oath required. For personal study only.

โœฆ Synopsis

Let D be a set with a probability measure +, +(D)=1, and let K be a compact subset of L q (D, +),

where the infimum is taken over all g n of the form g n = n i=1 a i , i , with arbitrary , i # K and a i # R. It is shown that for f # conv(K _ (&K )), under some mild restrictions, \ n ( f, K ) C q = n (K ) n &1ร‚2 , where = n (K ) ร„ 0 as nร„ . This fact is used to estimate the errors of certain neural net approximations. For the latter, also the lower estimates of errors are given.

๐Ÿ“œ SIMILAR VOLUMES

Uniform Approximation by Neural Networks
Uniform Approximation by Neural Networks
โœ Y. Makovoz ๐Ÿ“‚ Article ๐Ÿ“… 1998 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 262 KB

Let D/R d be a compact set and let 8 be a uniformly bounded set of D ร„ R functions. For a given real-valued function f defined on D and a given natural number n, we are looking for a good uniform approximation to f of the form n i=1 a i , i , with , i # 8, a i # R. Two main cases are considered: (1)

Properties and performance of orthogonal
Properties and performance of orthogonal neural network in function approximation
โœ Chieh F. Sher; Ching-Shiow Tseng; Chen-San Chen ๐Ÿ“‚ Article ๐Ÿ“… 2001 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 216 KB

Backpropagation neural network has been applied successfully to solving uncertain problems in many fields. However, unsolved drawbacks still exist such as the problems of local minimum, slow convergence speed, and the determination of initial weights and the number of processing elements. In this pa

Neural Networks and Chaos
Neural Networks and Chaos
โœ Walter J. Freeman ๐Ÿ“‚ Article ๐Ÿ“… 1994 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 294 KB