An effIcient pruning algorithm for sparselized higher-order neural networks

被引：0
|
作者：
Wang, YB [1 ]
Li, TX [1 ]
Li, AY [1 ]
Li, WC [1 ]
机构：
[1] Commun Univ China, Comp & Software Sch, Beijing, Peoples R China
来源：
ICAI '05: PROCEEDINGS OF THE 2005 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS 1 AND 2 | 2005年
关键词：
higher-order neural networks; redundant connection weights; sparselized higher-order neural networks; pruning algorithm; sunspots series;
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：
An efficient pruning algorithm for sparselized higher-older neural networks is proposed in this paper Using the algorithm a smallest architecture of higher-order neural network can be generated easily. To evaluate the good generalization ability an example of activity of sunspots series has been simulated and provided. As an important parameter VC dimension (Vapnik-Chervonenkis dimension) was applied for designing the training set. Simulation results are included to illustrate the effectiveness of the pruning algorithm and the good generalization ability of the sparselized higher-order neural network.
引用
收藏
页码：189 / 194
页数：6
相关论文
共 50 条
  • [11] Efficient Parallel Algorithm for Estimating Higher-order Polyspectra
    Tomlinson, Joseph
    Jeong, Donghui
    Kim, Juhan
    ASTRONOMICAL JOURNAL, 2019, 158 (03):
  • [12] Efficient modeling of higher-order dependencies in networks: from algorithm to application for anomaly detection
    Saebi, Mandana
    Xu, Jian
    Kaplan, Lance M.
    Ribeiro, Bruno
    Chawla, Nitesh V.
    EPJ DATA SCIENCE, 2020, 9 (01)
  • [13] Efficient modeling of higher-order dependencies in networks: from algorithm to application for anomaly detection
    Mandana Saebi
    Jian Xu
    Lance M. Kaplan
    Bruno Ribeiro
    Nitesh V. Chawla
    EPJ Data Science, 9
  • [14] LEARNING AND ENCODING HIGHER-ORDER RULES IN NEURAL NETWORKS
    LEVINE, DS
    BEHAVIOR RESEARCH METHODS INSTRUMENTS & COMPUTERS, 1995, 27 (02): : 178 - 182
  • [15] Graph Neural Network for Higher-Order Dependency Networks
    Jin, Di
    Gong, Yingli
    Wang, Zhiqiang
    Yu, Zhizhi
    He, Dongxiao
    Huang, Yuxiao
    Wang, Wenjun
    PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22), 2022, : 1622 - 1630
  • [16] Higher-order Clustering and Pooling for Graph Neural Networks
    Duval, Alexandre
    Malliaros, Fragkiskos
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022, 2022, : 426 - 435
  • [17] Neural Predicting Higher-order Patterns in Temporal Networks
    Liu, Yunyu
    Ma, Jianzhu
    Li, Pan
    PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22), 2022, : 1340 - 1351
  • [18] Theory and development of higher-order CMAC neural networks
    Lane, Stephen H.
    Handelman, David A.
    Gelfand, Jack J.
    IEEE Control Systems Magazine, 1992, 12 (02): : 23 - 30
  • [19] Weisfeiler and Leman Go Neural: Higher-Order Graph Neural Networks
    Morris, Christopher
    Ritzert, Martin
    Fey, Matthias
    Hamilton, William L.
    Lenssen, Jan Eric
    Rattan, Gaurav
    Grohe, Martin
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 4602 - 4609
  • [20] An Efficient Randomized Algorithm for Higher-Order Abstract Voronoi Diagrams
    Cecilia Bohler
    Rolf Klein
    Chih-Hung Liu
    Algorithmica, 2019, 81 : 2317 - 2345
12345