咨询与建议

限定检索结果

文献类型

  • 31 篇 期刊文献
  • 7 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

  • 35 篇 工学
    • 34 篇 计算机科学与技术...
    • 7 篇 电气工程
    • 5 篇 控制科学与工程
    • 5 篇 软件工程
    • 2 篇 机械工程
    • 1 篇 材料科学与工程(可...
  • 8 篇 管理学
    • 8 篇 管理科学与工程(可...
  • 4 篇 理学
    • 4 篇 数学

主题

  • 38 篇 constructive alg...
  • 6 篇 neural networks
  • 3 篇 cascade
  • 3 篇 feedforward neur...
  • 2 篇 pruning algorith...
  • 2 篇 genetic programm...
  • 2 篇 b-splines
  • 2 篇 route expansion
  • 2 篇 container loadin...
  • 2 篇 pattern classifi...
  • 2 篇 at_casper
  • 2 篇 cascor
  • 2 篇 a_casper
  • 2 篇 agent-based simu...
  • 2 篇 algorithmic skel...
  • 2 篇 genetic algorith...
  • 2 篇 machine learning
  • 2 篇 combinatorial op...
  • 2 篇 node insertion
  • 2 篇 load planing

机构

  • 1 篇 univ nottingham ...
  • 1 篇 univ pisa dipart...
  • 1 篇 heathrow airport...
  • 1 篇 zentrumfuer tele...
  • 1 篇 inria sophia ant...
  • 1 篇 univ paris dider...
  • 1 篇 ohio state univ ...
  • 1 篇 univ algarve ctr...
  • 1 篇 univ paris est l...
  • 1 篇 univ calif los a...
  • 1 篇 ibm tj watson re...
  • 1 篇 rhein westfal th...
  • 1 篇 ulster univ sch ...
  • 1 篇 school of electr...
  • 1 篇 centre for trans...
  • 1 篇 northern ireland...
  • 1 篇 univ catholique ...
  • 1 篇 khulna univ engn...
  • 1 篇 assiut univ civi...
  • 1 篇 duluth inst adv ...

作者

  • 2 篇 reodecha manop
  • 2 篇 chaovalitwongse ...
  • 2 篇 werner frank
  • 2 篇 loulergue freder...
  • 2 篇 tesson julien
  • 2 篇 jungwattanakit j...
  • 2 篇 araya ignacio
  • 1 篇 sharma sudhir ku...
  • 1 篇 delgado m
  • 1 篇 siddique nazmul
  • 1 篇 nunez eduardo
  • 1 篇 robertz d
  • 1 篇 delogu rita
  • 1 篇 johan w. joubert
  • 1 篇 de pauw t
  • 1 篇 botzheim janos
  • 1 篇 draghici s
  • 1 篇 bianucci am
  • 1 篇 zennaro marino
  • 1 篇 f. sittner

语言

  • 34 篇 英文
  • 4 篇 其他
检索条件"主题词=constructive algorithms"
38 条 记 录,以下是31-40 订阅
排序:
A constructive approach to calculating lower entropy bounds
收藏 引用
NEURAL PROCESSING LETTERS 1999年 第1期9卷 1-12页
作者: Beiu, V Draghici, S De Pauw, T Univ Calif Los Alamos Natl Lab Div NIS 1 Los Alamos NM 87545 USA Wayne State Univ Dept Comp Sci Vis & Neural Networks Lab Detroit MI 48202 USA Univ Catholique Louvain Dept Math B-1348 Louvain Belgium
This paper presents a constructive approach to estimating the size of a neural network necessary to solve a given classification problem. The results are derived using an information entropy approach in the context of... 详细信息
来源: 评论
Exploring constructive cascade networks
收藏 引用
IEEE TRANSACTIONS ON NEURAL NETWORKS 1999年 第6期10卷 1335-1350页
作者: Treadgold, NK Gedeon, TD Univ New S Wales Sch Engn & Comp Sci Sydney NSW Australia
constructive algorithms have proved to be powerful methods for training feedforward neural networks. An important property of these algorithms is generalization. A series of empirical studies were performed to examine... 详细信息
来源: 评论
A constructive NEURAL NETWORK ALGORITHM FOR FUNCTION APPROXIMATION USING LOCALLY FIT SIGMOIDS
收藏 引用
International Journal on Artificial Intelligence Tools 1998年 第3期7卷 373-398页
作者: TIM DRAELOS DON HUSH Department of Electrical and Computer Engineering University of New Mexico Albuquerque NM 87131 USA
A study of the function approximation capabilities of single hidden layer neural networks strongly motivates the investigation of constructive learning techniques as a means of realizing established error bounds. Lear... 详细信息
来源: 评论
Objective functions for training new hidden units in constructive neural networks
收藏 引用
IEEE TRANSACTIONS ON NEURAL NETWORKS 1997年 第5期8卷 1131-1148页
作者: Kwok, TY Yeung, DY Department of Computer Science Hong Kong University of Science and Technology
In this paper, we study a number of objective functions for training new hidden units in constructive algorithms for multilayer feedforward networks. The aim is to derive a class of objective functions the computation... 详细信息
来源: 评论
Training a neuron in sequential learning
收藏 引用
NEURAL PROCESSING LETTERS 1997年 第2期5卷 91-96页
作者: Poulard, H Hernandez, N ACTIA F-31432 TOULOUSEFRANCE
Among binary unit-based constructive algorithms, the Sequential Learning is particularly interesting for many reasons, the most significant one being its ability to treat real valued inputs without preprocessing. Howe... 详细信息
来源: 评论
A multi-output-layer perceptron
收藏 引用
NEURAL COMPUTING & APPLICATIONS 1996年 第1期4卷 10-20页
作者: Owens, FJ Zheng, GH Irvine, DA Northern Ireland Bioengineering Centre School of Electrical and Mechanical Engineering Faculty of Engineering University of Ulster at Jordanstown Newtownabbey Co. Antrim Northern Ireland
This paper investigates the possibility of improving the classification capability of single-layer and multilayer perceptrons by incorporating additional output layers. This Multi-Output-Layer Perceptron (MOLP) is a n... 详细信息
来源: 评论
Neural networks for monitoring of engine condition data
收藏 引用
Neural Computing & Applications 1993年 第1期1卷 96-102页
作者: Cumming, Simon Heathrow Airport Hounslow TW6 2JA British Airways plc E172 United Kingdom
Neural networks are being tested to monitor aircraft engine condition data, in addition to current techniques and newer methods such as knowledge-based systems or case-based reasoning, in order to increase safety and ... 详细信息
来源: 评论
Combining Prior Symbolic Knowledge and constructive Neural Network Learning
收藏 引用
Connection Science 1993年 第3-4期5卷 365-375页
作者: Fletcher, Justin Obradovic, Z. School of Electrical Engineering and Computer Science Washington State University Pullman WA 99164-2752 United States
来源: 评论