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
  • [21] Neural-network modeling
    Furrer, D
    Thaler, S
    ADVANCED MATERIALS & PROCESSES, 2005, 163 (11): : 42 - 46
  • [22] Neural-network superresolution
    Torrieri, D
    Bakhru, K
    MILCOM 97 PROCEEDINGS, VOLS 1-3, 1997, : 1594 - 1598
  • [23] Neural-network wavefunctions
    Kaitlin McCardle
    Nature Computational Science, 2022, 2 : 284 - 284
  • [24] NEURAL-NETWORK HEURISTICS
    JOSIN, G
    BYTE, 1987, 12 (11): : 183 - &
  • [25] A SYNERGETIC NEURAL-NETWORK
    NAKAGAWA, M
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 1995, E78A (03) : 412 - 423
  • [26] Neural-network wavefunctions
    McCardle, Kaitlin
    NATURE COMPUTATIONAL SCIENCE, 2022, 2 (05): : 284 - 284
  • [27] Tight Approximation Bounds for the Seminar Assignment Problem
    Bar-Noy, Amotz
    Rabanca, George
    APPROXIMATION AND ONLINE ALGORITHMS (WAOA 2016), 2017, 10138 : 170 - 182
  • [28] Tight Bounds for the Approximation Ratio of the Hypervolume Indicator
    Bringmann, Karl
    Friedrich, Tobias
    PARALLEL PROBLEMS SOLVING FROM NATURE - PPSN XI, PT I, 2010, 6238 : 607 - +
  • [29] Hybrid neural-network FEM approximation of diffusion coefficient in elliptic and parabolic Problems
    Cen, Siyu
    Jin, Bangti
    Quan, Qimeng
    Zhou, Zhi
    IMA JOURNAL OF NUMERICAL ANALYSIS, 2023, 44 (05) : 3059 - 3093
  • [30] An application of sequential neural-network approximation for sitting and sizing passive harmonic filters
    Low, Chinyao
    Chang, Ying-Pin
    Hung, Shih-Yu
    EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (02) : 2910 - 2920
12345