期刊
IEEE TRANSACTIONS ON INFORMATION THEORY
卷 58, 期 2, 页码 1203-1214出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIT.2011.2169531
关键词
Dictionary-based computational models; high-dimensional approximation and optimization; model complexity; polynomial upper bounds
资金
- Georgetown University
- GA CR [201/08/1744, P202/11/1368]
- Institutional Research Plan [AV0Z10300504]
- Italian Ministry for University and Research
- CNR-AV CR
- MSMT [ME10023]
The role of input dimension d is studied in approximating, in various norms, target sets of d-variable functions using linear combinations of adjustable computational units. Results from the literature, which emphasize the number n of terms in the linear combination, are reformulated, and in some cases improved, with particular attention to dependence on d. For worst-case error, upper bounds are given in the factorized form xi(d)kappa(n), where kappa is nonincreasing (typically kappa(n) similar to n(-1/2)). Target sets of functions are described for which the function xi is a polynomial. Some important cases are highlighted where xi decreases to zero as d -> infinity. For target functions, extent (e.g., the size of domains in where they are defined), scale (e.g., maximum norms of target functions), and smoothness (e.g., the order of square-integrable partial derivatives) may depend on, and the influence of such dimension-dependent parameters on model complexity is considered. Results are applied to approximation and solution of optimization problems by neural networks with perceptron and Gaussian radial computational units.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据