Model Complexity of Neural Networks in High-Dimensional Approximation

被引：0

作者：

Kurkova, Vera ^{[1
]}

机构：

[1] Acad Sci Czech Republic, Inst Comp Sci, Prague 18207, Czech Republic

来源：

RECENT ADVANCES IN INTELLIGENT ENGINEERING SYSTEMS | 2012年 / 378卷

关键词：

SUPERPOSITIONS; RATES; TRACTABILITY;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The role of dimensionality in approximation by neural networks is investigated. Methods from nonlinear approximation theory are used to describe sets of functions which can be approximated by neural networks with a polynomial dependence of model complexity on the input dimension. The results are illustrated by examples of Gaussian radial networks.

引用

页码：151 / 160

页数：10

共 50 条

[21] High-dimensional distribution generation through deep neural networks
Perekrestenko, Dmytro
Eberhard, Leandre
Bolcskei, Helmut
PARTIAL DIFFERENTIAL EQUATIONS AND APPLICATIONS, 2021, 2 (05):
[22] Robust high-dimensional memory-augmented neural networks
Karunaratne, Geethan
Schmuck, Manuel
Le Gallo, Manuel
Cherubini, Giovanni
Benini, Luca
Sebastian, Abu
Rahimi, Abbas
NATURE COMMUNICATIONS, 2021, 12 (01)
[23] Construction of high-dimensional neural networks by linear connections of matrices
Kobayashi, M
Muramatsu, J
Yamazaki, H
ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 2003, 86 (11): : 38 - 45
[24] Interpretable Approximation of High-Dimensional Data
Potts, Daniel
Schmischke, Michael
SIAM JOURNAL ON MATHEMATICS OF DATA SCIENCE, 2021, 3 (04): : 1301 - 1323
[25] Approximation of high-dimensional parametric PDEs
Cohen, Albert
DeVore, Ronald
ACTA NUMERICA, 2015, 24 : 1 - 159
[26] LAPLACE APPROXIMATION OF HIGH-DIMENSIONAL INTEGRALS
SHUN, ZM
MCCULLAGH, P
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1995, 57 (04): : 749 - 760
[27] High-Dimensional Indexing by Sparse Approximation
Borges, Pedro
Mourao, Andre
Magalhaes, Joao
ICMR'15: PROCEEDINGS OF THE 2015 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, 2015, : 163 - 170
[28] Deep neural network approximation for high-dimensional elliptic PDEs with boundary conditions
Grohs, Philipp
Herrmann, Lukas
IMA JOURNAL OF NUMERICAL ANALYSIS, 2022, 42 (03) : 2055 - 2082
[29] High-dimensional Apollonian networks
Zhang, ZZ
Comellas, F
Fertin, G
Rong, LL
JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 2006, 39 (08): : 1811 - 1818
[30] Training neural networks on high-dimensional data using random projection
Wojcik, Piotr Iwo
Kurdziel, Marcin
PATTERN ANALYSIS AND APPLICATIONS, 2019, 22 (03) : 1221 - 1231

← 1 2 3 4 5 →