Riemannian-based neural network method for solving canonical correlation analysis

被引：0
|
作者：
Zhuo-Cheng Xie [1 ]
Ming Wang [1 ]
Yu-Hang Wang [1 ]
Huan Ren [1 ]
机构：
[1] School of Mathematical Sciences, Jiangxi Science and Technology Normal University, Nanchang
来源：
Computational and Applied Mathematics | 2025年 / 44卷 / 5期
基金：
中国国家自然科学基金;
关键词：
Canonical correlation analysis; Generalized Stiefel manifold; Neural network method; Riemannian gradient;
D O I：
10.1007/s40314-025-03197-9
中图分类号：
学科分类号：
摘要：
Canonical correlation analysis is a classic statistical technique. In this paper, we develop a neural network method based on the Riemannian gradient for solving canonical correlation analysis problems. For the theoretical analysis, the geometric dynamics properties of this method are investigated. Numerical experiments indicate the feasibility and effectiveness of the proposed neural network method. © The Author(s) under exclusive licence to Sociedade Brasileira de Matemática Aplicada e Computacional 2025.
引用
收藏
相关论文
共 50 条
  • [11] Research of Coupling Model of Canonical Correlation Analysis and RBF Neural Network on Atmosphere Environmental Quality
    Gong, Minqing
    Sun, Mingwei
    Jin, Mingzhong
    2012 2ND INTERNATIONAL CONFERENCE ON APPLIED ROBOTICS FOR THE POWER INDUSTRY (CARPI), 2012, : 668 - 671
  • [12] Multi-scale Sentiment Classification Using Canonical Correlation Analysis on Riemannian Manifolds
    Dai, Shuanglu
    Xu, Xingzhong
    Jiang, Bitian
    Man, Hong
    PROCEEDINGS OF 2016 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM), 2016, : 144 - 147
  • [13] Canonical Correlation Analysis for Detecting Changes in Network Structure
    O'Sullivan, Aidan
    Adams, Niall M.
    Rezek, Iead
    12TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW 2012), 2012, : 250 - 257
  • [14] Solving the SSVEP Paradigm Using the Nonlinear Canonical Correlation Analysis Approach
    De la Cruz-guevara, Danni Rodrigo
    Alfonso-Morales, Wilfredo
    Caicedo-Bravo, Eduardo
    SENSORS, 2021, 21 (16)
  • [15] Motion impedance cardiography denoising method based on canonical correlation analysis and coherence analysis
    Xie, Yao
    Yu, Honglong
    Xie, Qilian
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 86
  • [16] Spontaneous recovery of version by Canonical Correlation Analysis Network
    Lai, PL
    PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 862 - 866
  • [17] Canonical correlation analysis based on information theory
    Yin, XR
    JOURNAL OF MULTIVARIATE ANALYSIS, 2004, 91 (02) : 161 - 176
  • [18] Neural network method for solving fractional diffusion equations
    Qu, Haidong
    She, Zihang
    Liu, Xuan
    APPLIED MATHEMATICS AND COMPUTATION, 2021, 391
  • [19] SUPERVISED CANONICAL CORRELATION ANALYSIS OF DATA ON SYMMETRIC POSITIVE DEFINITE MANIFOLDS BY RIEMANNIAN DIMENSIONALITY REDUCTION
    Fallah, Faezeh
    Yang, Bin
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 8369 - 8373
  • [20] A WEB COMMUNITY-BASED VIDEO RETRIEVAL METHOD USING CANONICAL CORRELATION ANALYSIS
    Hatakeyama, Yasutaka
    Ogawa, Takahiro
    Asamizu, Satoshi
    Haseyama, Miki
    2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, : 805 - +
12345