咨询与建议

限定检索结果

文献类型

  • 28 篇 期刊文献
  • 10 篇 会议

馆藏范围

  • 38 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 32 篇 工学
    • 23 篇 计算机科学与技术...
    • 16 篇 电气工程
    • 9 篇 控制科学与工程
    • 4 篇 软件工程
    • 2 篇 仪器科学与技术
    • 2 篇 电子科学与技术(可...
    • 1 篇 力学(可授工学、理...
    • 1 篇 机械工程
    • 1 篇 信息与通信工程
  • 8 篇 理学
    • 7 篇 数学
    • 1 篇 地球物理学
    • 1 篇 统计学(可授理学、...
  • 6 篇 管理学
    • 6 篇 管理科学与工程(可...
  • 2 篇 医学
    • 2 篇 基础医学(可授医学...
    • 2 篇 临床医学
  • 1 篇 经济学
    • 1 篇 理论经济学

主题

  • 38 篇 nonlinear functi...
  • 5 篇 reinforcement le...
  • 5 篇 neural networks
  • 3 篇 function approxi...
  • 3 篇 actor-critic
  • 3 篇 radial basis fun...
  • 2 篇 nonlinear functi...
  • 2 篇 regression analy...
  • 2 篇 incremental lear...
  • 2 篇 economic growth.
  • 2 篇 classification
  • 2 篇 policy gradient
  • 2 篇 artificial neura...
  • 2 篇 production funct...
  • 1 篇 thermal stabilit...
  • 1 篇 mahalanobis dist...
  • 1 篇 piecewise-linear...
  • 1 篇 hinging hyperpla...
  • 1 篇 correlation-awar...
  • 1 篇 representation l...

机构

  • 2 篇 shahid beheshti ...
  • 2 篇 henan univ sci &...
  • 1 篇 faculty of engin...
  • 1 篇 google res mount...
  • 1 篇 southwest petr u...
  • 1 篇 amirkabir univ t...
  • 1 篇 fujian normal un...
  • 1 篇 yonsei univ dept...
  • 1 篇 austrian acad sc...
  • 1 篇 natl i lan univ ...
  • 1 篇 cent queensland ...
  • 1 篇 getac technol co...
  • 1 篇 department of st...
  • 1 篇 city univ hong k...
  • 1 篇 college of autom...
  • 1 篇 qnap syst inc ta...
  • 1 篇 nanjing univ sci...
  • 1 篇 naist informat s...
  • 1 篇 avic xi''an figh...
  • 1 篇 heriot watt univ...

作者

  • 3 篇 salimi-badr armi...
  • 2 篇 zhang tong
  • 2 篇 ebadzadeh mohamm...
  • 2 篇 zhu junlong
  • 2 篇 zheng ruijuan
  • 1 篇 murata n
  • 1 篇 yu yu-hsiang
  • 1 篇 hao hu
  • 1 篇 jihong shen
  • 1 篇 wang xueqi
  • 1 篇 venayagamoorthy ...
  • 1 篇 tarela jm
  • 1 篇 erlina tati
  • 1 篇 kirby michael j.
  • 1 篇 park jb
  • 1 篇 breiman l
  • 1 篇 chen c. l. phili...
  • 1 篇 iannella n
  • 1 篇 yan shengnan
  • 1 篇 zhao xuhui

语言

  • 32 篇 英文
  • 5 篇 其他
  • 1 篇 中文
检索条件"主题词=Nonlinear function approximation"
38 条 记 录,以下是31-40 订阅
排序:
Adaptive bound reduced-form genetic algorithms for B-spline neural network training
收藏 引用
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2004年 第11期E87D卷 2479-2488页
作者: Wang, WY Tao, CW Chang, CG Fu Jen Catholic Univ Dept Elect Engn Taipei 24205 Taiwan Natl I Lan Univ Dept Elect Engn Ilan Taiwan
In this paper, an adaptive bound reduced-form genetic algorithm (ABRGA) to tune the control points of B-spline neural networks is proposed. It is developed not only to search for the optimal control points but also to... 详细信息
来源: 评论
Digital design of sigmoid approximator for artificial neural networks
收藏 引用
ELECTRONICS LETTERS 2002年 第1期38卷 35-37页
作者: Basterretxea, K Tarela, JM del Campo, I Euskal Herriko Unibertsitatea EHUUPV EUITI Elekt & Telekomunikazio Saila Bilbao 48012 Basque Country Spain Euskal Herriko Unibertsitatea UPV EHU Zientzi Fak Leioa 48940 Basque Country Spain
A digital design for piecewise-linear (PWL) approximation to the sigmoid function is presented. Circuit operation is based on a recursive algorithm that uses lattice operators max and min to approximating nonlinear fu... 详细信息
来源: 评论
Error bounds for approximation with neural networks
收藏 引用
JOURNAL OF approximation THEORY 2001年 第2期112卷 235-250页
作者: Burger, M Neubauer, A Johannes Kepler Univ Linz Inst Ind Math A-4040 Linz Austria
In this paper we prove convergence rates for the problem of approximating functions f by neural networks and similar constructions. We show that the rates are the better the smoother the activation functions are, prov... 详细信息
来源: 评论
Control of chaotic dynamical systems using radial basis function network approximators
收藏 引用
INFORMATION SCIENCES 2000年 第1-4期130卷 165-183页
作者: Kim, KB Park, JB Choi, YH Chen, GR Univ Houston Dept Elect & Comp Engn Houston TX 77204 USA DAEWOO Elect Co Ltd Kyonggi South Korea Yonsei Univ Dept Elect Engn Seoul 120749 South Korea Kyonggi Univ Dept Elect Engn Kyonggi 442760 South Korea
This paper presents a general control method based on radial basis function networks (RBFNs) for chaotic dynamical systems. For many chaotic systems that can be decomposed into a sum of a linear and a nonlinear part, ... 详细信息
来源: 评论
On the hinge-finding algorithm for hinging hyperplanes
收藏 引用
IEEE TRANSACTIONS ON INFORMATION THEORY 1998年 第3期44卷 1310-1319页
作者: Pucar, P Sjoberg, J Saab AB Saab Aerosp Gripen S-58188 Linkoping Sweden Chalmers Univ Technol Dept Signals & Syst S-41296 Gothenburg Sweden
This correspondence concerns the estimation algorithm for hinging hyperplane (HH) models, a piecewise-linear model for approximating functions of several variables, suggested in Breiman [1], The estimation algorithm i... 详细信息
来源: 评论
Identification of time-varying nonlinear systems using minimal radial basis function neural networks
收藏 引用
IEE PROCEEDINGS-CONTROL THEORY AND APPLICATIONS 1997年 第2期144卷 202-208页
作者: Yingwei, L Sundararajan, N Saratchandran, P School of Electrical and Electronic Engineering Nanyang Technological University Singapore Republic of Singapore
An identification algorithm for time-varying nonlinear systems using a sequential learning scheme with a minimal radial basis function neural network (RBFNN) is presented. The learning algorithm combines the growth cr... 详细信息
来源: 评论
approximation bounds of three-layered neural networks - A theorem on an integral transform with ridge functions
收藏 引用
ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE 1996年 第3期79卷 23-33页
作者: Murata, N Member Faculty of Engineering the University of Tokyo Bunkyo-ku Tokyo Japan 113
Neural networks have attracted attention due to their capability to perform nonlinear function approximation. In this paper, in order to better understand this capability, a new theorem on an integral transform was de... 详细信息
来源: 评论
HINGING HYPERPLANES FOR REGRESSION, CLASSIFICATION, AND function approximation
收藏 引用
IEEE TRANSACTIONS ON INFORMATION THEORY 1993年 第3期39卷 999-1013页
作者: BREIMAN, L Department of Statistics University of California Berkeley Berkeley CA USA
A hinge function y=h(x) consists of two hyperplanes continuously joined together at a hinge. In regression (prediction), classification (pattern recognition), and noiseless function approximation, use of sums of hinge... 详细信息
来源: 评论