منابع مشابه
Fundamentality of Ridge Functions
For a given integer d, 1 ≤ d ≤ n − 1, let Ω be a subset of the set of all d × n real matrices. Define the subspace M(Ω) = span{g(Ax) : A ∈ Ω, g ∈ C(IR, IR)} . We give necessary and sufficient conditions on Ω so that M(Ω) is dense in C(IR, IR) in the topology of uniform convergence on compact subsets. This generalizes work of Vostrecov and Kreines. We also consider some related problems. §
متن کاملTwo Conceptions of Fundamentality
This article aims to show that fundamentality is construed differently in the two most prominent strategies of analysis we find in physical science and engineering today: (1) atomistic, reductive analysis and (2) Systems analysis. Correspondingly, atomism is the conception according to which the simplest (smallest) indivisible entity of a certain kind is most fundamental; while systemism, as wi...
متن کاملRidge Functions, Sigmoidal Functions and Neural Networks
This paper considers mainly approximation by ridge functions. Fix a point a 2 IR n and a function g : IR ! IR. Then the function f : IR n ! IR deened by f (x) = g(ax), x 2 IR n , is a ridge or plane wave function. A sigmoidal function is a particular example of the function g which closely resembles 1 at 1 and 0 at ?1. This paper discusses approximation problems involving general ridge function...
متن کاملOn the Fundamentality of Symmetries
That symmetry is fundamental to modern physics is a view frequently expressed by physicists. In his popular expositions Steven Weinberg, for example, has aimed above all to communicate his conviction that ‘symmetries are fundamental, and possibly all that one needs to learn about the physical world beyond quantum mechanics itself’.1 His fellow particle physicist Abdus Salam has argued similarly...
متن کاملRidgelets: Estimating with Ridge Functions
Feedforward neural networks, projection pursuit regression, and more generally, estimation via ridge functions have been proposed as an approach to bypass the curse of dimensionality and are now becoming widely applied to approximation or prediction in applied sciences. To address problems inherent to these methods – ranging from the construction of neural networks to their efficiency and capab...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Approximation Theory
سال: 1993
ISSN: 0021-9045
DOI: 10.1006/jath.1993.1104