《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (1): 16-25.DOI: 10.11772/j.issn.1001-9081.2021010171

• 人工智能 • 上一篇    下一篇

基于随机特征映射的四层多核学习方法

杨悦(), 王士同   

  1. 江南大学 人工智能与计算机学院,江苏 无锡 214122
  • 收稿日期:2021-01-29 修回日期:2021-04-24 接受日期:2021-05-10 发布日期:2021-06-04 出版日期:2022-01-10
  • 通讯作者: 杨悦
  • 作者简介:杨悦(1995—),女,云南玉溪人,硕士研究生,主要研究方向:机器学习、神经网络
    王士同(1964—),男,江苏扬州人,教授,博士生导师,硕士,CCF会员,主要研究方向:人工智能、模式识别。
  • 基金资助:
    江苏省自然科学基金资助项目(BK20191331)

Four-layer multiple kernel learning method based on random feature mapping

Yue YANG(), Shitong WANG   

  1. School of Artificial Intelligence and Computer Science,Jiangnan University,Wuxi Jiangsu 214122,China
  • Received:2021-01-29 Revised:2021-04-24 Accepted:2021-05-10 Online:2021-06-04 Published:2022-01-10
  • Contact: Yue YANG
  • About author:YANG Yue, born in 1995, M. S. candidate. Her research interests include machine learning, neural network.
    WANG Shitong, born in 1964, M. S., professor. His research interests include artificial intelligence, pattern recognition.
  • Supported by:
    Natural Science Foundation of Jiangsu Province(BK20191331)

摘要:

针对单核网络模型的核函数选择无理论依据以及基于随机特征映射的四层神经网络(FRMFNN)节点规模过大的问题,提出了一种基于随机特征映射的四层多核学习神经网络(MK-FRMFNN)算法。首先,把原始输入特征通过特定的随机映射算法转化为随机映射特征;然后,经过不同的随机核映射生成多个基本核矩阵;最后,将基本核矩阵组成合成核矩阵,并通过输出权重连接到输出层。对原始特征进行随机映射的权重是根据任意连续采样概率分布随机生成的,不需要训练更新,且对输出层的权重使用岭回归伪逆算法进行快速求解,从而避免了反复迭代耗时的训练过程。MK-FRMFNN在基本核映射时引入了不同的随机权重矩阵,生成的合成核矩阵不仅可以综合各种核函数的优势,而且可以集合各种随机分布函数的特性,使数据在新的特征空间中获得更好的特征选择和表达效果。理论和实验分析表明,与宽度学习系统(BLS)及FRMFNN等单核模型相比,MK-FRMFNN模型的节点规模减小了2/3左右,且分类性能稳定;与主流的多种多核模型相比,MK-FRMFNN模型能够对大样本数据集进行学习,并且分类性能明显更优。

关键词: 随机特征映射, 稀疏自动编码器, 多核学习, 岭回归, 正则化

Abstract:

Since there is no perfect theoretical basis for the selection of kernel function in single kernel network models, and the network node size of Four-layer Neural Network based on Randomly Feature Mapping (FRFMNN) is excessively large, a Four-layer Multiple Kernel Neural Network based on Randomly Feature Mapping (MK-FRFMNN) algorithm was proposed. Firstly, the original input features were transformed into randomly mapped features by a specific random mapping algorithm. Then, multiple basic kernel matrices were generated through different random kernel mappings. Finally, the synthetic kernel matrix formed by basic kernel matrices was linked to the output layer through the output weights. Since the weights of random mapping of original features were randomly generated according to the random continuous sampling probability distribution randomly, without the need of updates of the weights, and the weights of the output layer were quickly solved by the ridge regression pseudo inverse algorithm, thus avoiding the time-consuming training process of the repeated iterations. Different random weight matrices were introduced into the basic kernel mapping of MK-FRFMNN. the generated synthetic kernel matrix was able to not only synthesize the advantages of various kernel functions, but also integrate the characteristics of various random distribution functions, to obtain better feature selection and expression effect in the new feature space. Theoretical and experimental analyses show that, compared with the single kernel models such as Broad Learning System (BLS) and FRMFNN, MK-FRMFNN model has the node size reduced by about 2/3 with stable classification performance; compared with mainstream multiple kernel models, MK-FRMFNN model can learn large sample datasets, and has better performance in classification.

Key words: random feature mapping, sparse autoencoder, multiple kernel learning, ridge regression, regularization

中图分类号: