arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.19396cs.LGcs.CVcs.SYeess.SY
收藏

典型相关引导的深度神经网络

Canonical Correlation Guided Deep Neural Network

School of Automation, Central South University(中南大学自动化学院);Department of Electrical and Electronic Engineering, the Hong Kong Polytechnic University(香港理工大学电机及电子工程学系);Institute for Automatic Control and Complex Systems (AKS), University of Duisburg-Essen(杜伊斯堡-埃森大学自动控制与复杂系统研究所)

Zhiwen Chen, Siwen Mo, Haobin Ke, Steven X. Ding, Zhaohui Jiang, Chunhua Yang, Weihua Gui

AI总结:

本文提出典型相关引导的深度神经网络CCDNN,将典型相关作为约束而非最大化目标,并引入冗余滤波器,在重建、分类和预测任务上优于DCCA等方法。

摘要:

学习数据两个视图的表示,使得所得到的表示具有高度线性相关性,在机器学习中具有吸引力。本文提出了一种典型相关引导的学习框架,该框架可以通过深度神经网络(CCDNN)实现,以学习这种相关表示。这也是多元分析(MVA)与机器学习的一种新颖融合,可以看作是在神经网络的帮助下将MVA转化为端到端架构。与线性典型相关分析(CCA)、核CCA和深度CCA不同,在所提出的方法中,优化公式并不局限于最大化相关性,而是将典型相关作为约束条件,既保留了相关表示学习能力,又更侧重于优化公式所赋予的工程任务,例如重建、分类和预测。此外,为了减少相关性带来的冗余,设计了一个冗余滤波器。我们展示了CCDNN在各种任务上的性能。在MNIST数据集上的实验结果表明,CCDNN在均方误差和平均绝对误差方面比DCCA和DCCAE具有更好的重建性能。此外,我们还展示了所提出的网络在工业故障诊断和剩余使用寿命案例中的应用,分别用于分类和预测任务。与现有方法相比,所提出的方法在这两项任务中均表现出优越的性能。附录中还展示了借助残差连接将CCDNN扩展到更深层网络的内容。

英文摘要:

Learning representations of two views of data such that the resulting representations are highly linearly correlated is appealing in machine learning. In this paper, we present a canonical correlation guided learning framework, which allows to be realized by deep neural networks (CCDNN), to learn such a correlated representation. It is also a novel merging of multivariate analysis (MVA) and machine learning, which can be viewed as transforming MVA into end-to-end architectures with the aid of neural networks. Unlike the linear canonical correlation analysis (CCA), kernel CCA and deep CCA, in the proposed method, the optimization formulation is not restricted to maximize correlation, instead we make canonical correlation as a constraint, which preserves the correlated representation learning ability and focuses more on the engineering tasks endowed by optimization formulation, such as reconstruction, classification and prediction. Furthermore, to reduce the redundancy induced by correlation, a redundancy filter is designed. We illustrate the performance of CCDNN on various tasks. In experiments on MNIST dataset, the results show that CCDNN has better reconstruction performance in terms of mean squared error and mean absolute error than DCCA and DCCAE. Also, we present the application of the proposed network to industrial fault diagnosis and remaining useful life cases for the classification and prediction tasks accordingly. The proposed method demonstrates superior performance in both tasks when compared to existing methods. Extension of CCDNN to much more deeper with the aid of residual connection is also presented in appendix.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑