Tight bounds on rates of neural-network approximation

被引：0
|
作者：
Kurková, V
Sanguineti, M
机构：
[1] Acad Sci Czech Republ, Inst Comp Sci, Prague 18207 8, Czech Republic
[2] Univ Genoa, Dept Commun Comp & Syst Sci, I-16145 Genoa, Italy
来源：
ARTIFICIAL NEURAL NETWORKS-ICANN 2001, PROCEEDINGS | 2001年 / 2130卷
关键词：
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：
Complexity of neural networks measured by the number of hidden units is studied in terms of rates of approximation. Limitations of improvements of upper bounds of the order of O(n(-1/2)) on such rates are investigated for perceptron networks with some periodic and sigmoidal activation functions.
引用
收藏
页码：277 / 282
页数：6
相关论文
共 50 条
  • [31] LinSyn: Synthesizing Tight Linear Bounds for Arbitrary Neural Network Activation Functions
    Paulsen, Brandon
    Wang, Chao
    TOOLS AND ALGORITHMS FOR THE CONSTRUCTION AND ANALYSIS OF SYSTEMS, TACAS 2022, PT I, 2022, 13243 : 357 - 376
  • [32] Statistical inference, the bootstrap, and neural-network modeling with application to foreign exchange rates
    White, H
    Racine, J
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (04): : 657 - 673
  • [33] A NEURAL-NETWORK BASED TOOL
    SHEWHART, M
    IEEE SPECTRUM, 1992, 29 (02) : 6 - 6
  • [34] SOIL CLASSIFICATION BY NEURAL-NETWORK
    CAL, Y
    ADVANCES IN ENGINEERING SOFTWARE, 1995, 22 (02) : 95 - 97
  • [35] A NEURAL-NETWORK AUDIO SYNTHESIZER
    THORSON, M
    WARTHMAN, F
    HOLLER, M
    DR DOBBS JOURNAL, 1993, 18 (02): : 50 - &
  • [36] MULTIOBJECTIVE OPTIMIZATION OF NEURAL-NETWORK
    WANG, JC
    LU, WX
    SCIENCE IN CHINA SERIES B-CHEMISTRY LIFE SCIENCES & EARTH SCIENCES, 1995, 38 (08): : 971 - 978
  • [37] ON OPTIMAL NEURAL-NETWORK LEARNING
    WATKIN, TLH
    PHYSICA A, 1993, 200 (1-4): : 628 - 635
  • [38] A NEURAL-NETWORK MODEL OF CAUSALITY
    SUN, R
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (04): : 604 - 611
  • [39] NEURAL-NETWORK CLASSIFICATION AND FORMALIZATION
    FIESLER, E
    COMPUTER STANDARDS & INTERFACES, 1994, 16 (03) : 231 - 239
  • [40] THE HAMILTON NEURAL-NETWORK MODEL
    SHUAI, JW
    CHEN, ZX
    LIU, RT
    WU, BX
    PHYSICA A, 1995, 216 (1-2): : 20 - 31
12345