Decision region approximation by polynomials or neural networks

被引：6

作者：

Blackmore, KL ^{[1
]}

Williamson, RC ^{[1
]}

Mareels, IMY ^{[1
]}

机构：

[1] AUSTRALIAN NATL UNIV,DEPT ENGN,CANBERRA,ACT 0200,AUSTRALIA

来源：

IEEE TRANSACTIONS ON INFORMATION THEORY | 1997年 / 43卷 / 03期

基金：

澳大利亚研究理事会;

关键词：

classification; decision region; neural networks; polynomials; rate of approximation;

D O I：

10.1109/18.568700

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

We give degree of approximation results for decision regions which are defined by polynomial and neural network parametrizations. The volume of the misclassified region is used to measure the approximation error, and results for the degree of L-1 approximation of functions are used, For polynomial parametrizations, we show that the degree of approximation is at least 1, whereas for neural network parametrizations we prove the slightly weaker result that the degree of approximation is at least r, where r can be any number in the open interval (0, 1).

引用

页码：903 / 907

页数：5

共 50 条

[1] Approximation of algebraic and trigonometric polynomials by feedforward neural networks
Jian-Jun Wang
Bai-Li Chen
Chan-Yun Yang
[J]. Neural Computing and Applications, 2012, 21 : 73 - 80
[2] Approximation of algebraic and trigonometric polynomials by feedforward neural networks
Wang, Jian-Jun
Chen, Bai-Li
Yang, Chan-Yun
[J]. NEURAL COMPUTING & APPLICATIONS, 2012, 21 (01): : 73 - 80
[3] The Chebyshev-Polynomials-Based unified model neural networks for function approximation
Lee, TT
Jeng, JT
[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1998, 28 (06): : 925 - 935
[4] Chebyshev polynomials based (CPB) unified model neural networks for function approximation
Lee, TT
Jeng, JT
[J]. APPLICATIONS AND SCIENCE OF ARTIFICIAL NEURAL NETWORKS III, 1997, 3077 : 372 - 381
[5] On approximation of ultraspherical polynomials in the oscillatory region
Krasikov, Ilia
[J]. JOURNAL OF APPROXIMATION THEORY, 2017, 222 : 143 - 156
[6] Learning Polynomials with Neural Networks
Andoni, Alexandr
Panigrahy, Rina
Valiant, Gregory
Zhang, Li
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 32 (CYCLE 2), 2014, 32 : 1908 - 1916
[7] Emulation of Spline Networks Through Approximation of Polynomials and Step Function of Neural Networks with Cosine Modulated Symmetric Exponential Function
Sang-Wha Lee
Hae-Sang Song
[J]. Wireless Personal Communications, 2014, 79 : 2579 - 2594
[8] Emulation of Spline Networks Through Approximation of Polynomials and Step Function of Neural Networks with Cosine Modulated Symmetric Exponential Function
Lee, Sang-Wha
Song, Hae-Sang
[J]. WIRELESS PERSONAL COMMUNICATIONS, 2014, 79 (04) : 2579 - 2594
[9] Approximation by neural networks is not continuous
Kainen, PC
Kurková, V
Vogt, A
[J]. NEUROCOMPUTING, 1999, 29 (1-3) : 47 - 56
[10] Piecewise approximation and neural networks
Revayova, Martina
Torok, Csaba
[J]. KYBERNETIKA, 2007, 43 (04) : 547 - 559

← 1 2 3 4 5 →