Rate of convergence in density estimation using neural networks

被引：8
|
作者：
Modha, DS
Masry, E
机构：
[1] Dept. of Elec. and Comp. Engineering, Univ. of California at San Diego, San Diego, CA 92093-0407
来源：
NEURAL COMPUTATION | 1996年 / 8卷 / 05期
关键词：
D O I：
10.1162/neco.1996.8.5.1107
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Given Ni.i.d. observations {X(i)}(N)(i=1) taking values in a compact subset of R(d), such that p* denotes their common probability density function, we estimate p* from an exponential family of densities based on single hidden layer sigmoidal networks using a certain minimum complexity density estimation scheme. Assuming that p* possesses a certain exponential representation, we establish a rate of convergence, independent of the dimension d, for the expected Hellinger distance between the proposed minimum complexity density estimator and the true underlying density p*.
引用
收藏
页码：1107 / 1122
页数：16
相关论文
共 50 条
  • [41] Estimation of proper strain rate in the CRSC test using a artificial neural networks
    Chae, JS
    Park, HK
    Lee, S
    [J]. PROCEEDINGS OF THE TWELFTH (2002) INTERNATIONAL OFFSHORE AND POLAR ENGINEERING CONFERENCE, VOL 2, 2002, : 630 - 634
  • [42] On the rate of convergence of image classifiers based on convolutional neural networks
    Kohler, Michael
    Krzyzak, Adam
    Walter, Benjamin
    [J]. ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 2022, 74 (06) : 1085 - 1108
  • [43] Estimate of exponential convergence rate and exponential stability for neural networks
    Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, Hong Kong
    [J]. IEEE Trans Neural Networks, 6 (1487-1493):
  • [44] On the rate of convergence of image classifiers based on convolutional neural networks
    Michael Kohler
    Adam Krzyżak
    Benjamin Walter
    [J]. Annals of the Institute of Statistical Mathematics, 2022, 74 : 1085 - 1108
  • [45] Estimate of exponential convergence rate and exponential stability for neural networks
    Yi, Z
    Heng, PA
    Fu, AWC
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (06): : 1487 - 1493
  • [46] The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies
    Basri, Ronen
    Jacobs, David
    Kasten, Yoni
    Kritchman, Shira
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [47] Asymptotic Convergence Rate of Dropout on Shallow Linear Neural Networks
    Senen-Cerda, Albert
    Sanders, Jaron
    [J]. PROCEEDINGS OF THE ACM ON MEASUREMENT AND ANALYSIS OF COMPUTING SYSTEMS, 2022, 6 (02)
  • [48] Globally exponential stability analysis and estimation of the exponential convergence rate for neural networks with multiple time varying delays
    Zhang, HG
    Wang, ZS
    [J]. ADVANCES IN NATURAL COMPUTATION, PT 1, PROCEEDINGS, 2005, 3610 : 61 - 70
  • [49] Structured Neural Networks for Density Estimation and Causal Inference
    Chen, Asic
    Shi, Ruian
    Gao, Xiang
    Baptista, Ricardo
    Krishnan, Rahul G.
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [50] Fast crowd density estimation with convolutional neural networks
    Fu, Min
    Xu, Pei
    Li, Xudong
    Liu, Qihe
    Ye, Mao
    Zhu, Ce
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2015, 43 : 81 - 88
12345