Several realistic approaches to improve the generalization of feedforward neural networks

被引：0
|
作者：
Southeast Univ, Nanjing, China [1 ]
机构：
来源：
Tien Tzu Hsueh Pao | / 4卷 / [d]116-119期
关键词：
Classification (of information) - Feature extraction;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Based on a criterion for effective generalization of neural networks, several practical methods to improve the generalization performance of feedforward neural networks are proposed, including enhancing the feature extractor and classifier, and modifying the activation function of neuron. The simulation results on handwritten character recognition confirm that models have good generalization abilities.
引用
收藏
相关论文
共 50 条
  • [21] Optimized injection of noise in activation functions to improve generalization of neural networks
    Duan, Fabing
    Chapeau-Blondeau, Francois
    Abbott, Derek
    CHAOS SOLITONS & FRACTALS, 2024, 178
  • [22] How to improve the generalization ability of multi-layer neural networks
    Sebesta, V
    6TH WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL VI, PROCEEDINGS: INDUSTRIAL SYSTEMS AND ENGINEERING I, 2002, : 108 - 113
  • [23] PROPERTIES OF FEEDFORWARD NEURAL NETWORKS
    BUDINICH, M
    MILOTTI, E
    JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1992, 25 (07): : 1903 - 1914
  • [24] GENERALIZATION BY NEURAL NETWORKS
    SHEKHAR, S
    AMIN, MB
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 1992, 4 (02) : 177 - 185
  • [25] On generalization by neural networks
    Kak, SC
    INFORMATION SCIENCES, 1998, 111 (1-4) : 293 - 302
  • [26] Generalization capability of feedforward neural network for pattern recognition
    Huang, Deshuang
    Journal of Beijing Institute of Technology (English Edition), 1996, 5 (02): : 184 - 192
  • [27] Using wavelet–feedforward neural networks to improve air pollution forecasting in urban environments
    Daniel Dunea
    Alin Pohoata
    Stefania Iordache
    Environmental Monitoring and Assessment, 2015, 187
  • [28] A pseudoinverse learning algorithm for feedforward neural networks with stacked generalization applications to software reliability growth data
    Guo, P
    Lyu, MR
    NEUROCOMPUTING, 2004, 56 : 101 - 121
  • [29] Domain adversarial neural networks for domain generalization: when it works and how to improve
    Anthony Sicilia
    Xingchen Zhao
    Seong Jae Hwang
    Machine Learning, 2023, 112 : 2685 - 2721
  • [30] Domain adversarial neural networks for domain generalization: when it works and how to improve
    Sicilia, Anthony
    Zhao, Xingchen
    Hwang, Seong Jae
    MACHINE LEARNING, 2023, 112 (07) : 2685 - 2721
12345