A Polynomial Kernel Induced Distance Metric to Improve Deep Transfer Learning for Fault Diagnosis of Machines

10.1109/TNN.2010.2091281

10.1016/j.ymssp.2007.07.013

0

kingma, 0, Adam: A method for stochastic optimization, Proc Int Conf Learn Representations

maaten, 2008, Visualizing data using t-SNE, J Mach Learn Res, 9, 2579

10.1109/ACCESS.2018.2890566

10.1109/ACCESS.2018.2878491

10.1016/j.ymssp.2018.12.051

10.1109/SDPC.2018.8664814

10.1109/TII.2018.2864759

10.3390/app8122357

10.1109/ACCESS.2018.2837621

10.1109/TIE.2018.2868023

10.1016/j.knosys.2018.12.019

10.1109/ICCV.2013.274

yosinski, 0, How transferable are features in deep neural networks, Proc Adv Neural Inf Process Syst, 3320

10.1109/TIE.2018.2877090

10.1109/CVPR.2016.90

10.1109/TIE.2016.2519325

10.1109/TKDE.2009.191

lee, 0, Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks, Proc Int Conf Mach Learn, 2

10.1016/j.ymssp.2017.06.022

10.1109/TSMC.2017.2754287

10.1109/TIE.2016.2627020

10.1016/j.ymssp.2018.05.050

10.1016/j.neucom.2018.05.021

10.1016/j.ymssp.2017.11.024

10.1007/978-3-030-01424-7_27

gretton, 2012, A kernel two-sample test, J Mach Learn Res, 13, 723

10.1109/TKDE.2016.2554549

10.1016/j.neucom.2016.11.063

10.1109/MSP.2017.2740460

nair, 0, Rectified linear units improve restricted Boltzmann machines, Proc Int Conf Mach Learn, 807

zellinger, 0, Central moment discrepancy (CMD) for domain-invariant representation learning, Proc Int Conf Learn Representations