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 1711.04450cs.CV
收藏

深度神经网络的全迁移学习及其在脓毒症分类中的应用

All-Transfer Learning for Deep Neural Networks and its Application to Sepsis Classification

Panasonic Corporation(松下公司);Tokyo Institute of Technology(东京工业大学)

Yoshihide Sawada, Yoshikuni Sato, Toru Nakada, Kei Ujimoto, Nobuhiro Hayashi

摘要:

在这篇文章中,我们提出了一种用于深度神经网络(DNN)的迁移学习方法。深度学习已经在许多应用中得到广泛应用。然而,当大量训练数据不可用时,应用深度学习是有问题的。解决这个问题的传统方法之一是DNN的迁移学习。在图像识别领域,用于DNN的最先进的迁移学习方法重用在源域数据上训练的参数,除了输出层之外。然而,当目标域数据量非常小时,这种方法可能导致较差的分类性能。为了解决这个问题,我们提出了一种名为All-Transfer深度学习的方法,它可以传输DNN的所有参数。该方法利用源领域知识计算源标签和目标标签之间的关系。我们将我们的方法应用于实际的二维电泳图像~(2-DE图像)分类,以确定个体是否患有脓毒症;首次尝试将分类方法应用于蛋白质组学的2-DE图像,这已经引起了相当大的关注,作为基因组学的延伸。结果表明,我们提出的方法优于传统的迁移学习方法的DNN。

英文摘要:

In this article, we propose a transfer learning method for deep neural networks (DNNs). Deep learning has been widely used in many applications. However, applying deep learning is problematic when a large amount of training data are not available. One of the conventional methods for solving this problem is transfer learning for DNNs. In the field of image recognition, state-of-the-art transfer learning methods for DNNs re-use parameters trained on source domain data except for the output layer. However, this method may result in poor classification performance when the amount of target domain data is significantly small. To address this problem, we propose a method called All-Transfer Deep Learning, which enables the transfer of all parameters of a DNN. With this method, we can compute the relationship between the source and target labels by the source domain knowledge. We applied our method to actual two-dimensional electrophoresis image~(2-DE image) classification for determining if an individual suffers from sepsis; the first attempt to apply a classification approach to 2-DE images for proteomics, which has attracted considerable attention as an extension beyond genomics. The results suggest that our proposed method outperforms conventional transfer learning methods for DNNs.

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。

↑