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 1611.04499stat.MLcs.LG
收藏

使用最后一个内核的深度学习中的后训练

Post Training in Deep Learning with Last Kernel

CMLA, ENS Paris-Saclay, CNRS(巴黎萨克雷高等师范学校数学及其应用中心,法国国家科学研究中心);Université Paris-Saclay(巴黎萨克雷大学)

Thomas Moreau, Julien Audiffren

摘要:

深度学习方法的主要挑战之一是选择合适的训练策略。特别是,额外的步骤,如无监督的预训练,已被证明可以大大提高深层结构的性能。在本文中,我们提出了一个额外的训练步骤,称为后训练,它只优化网络的最后一层。我们表明,这个过程可以分析的内核理论的背景下,第一层计算嵌入的数据和最后一层的统计模型,以解决这个嵌入的基础上的任务。这一步确保数据的嵌入或表示以最佳方式用于所考虑的任务。然后在具有各种数据集的多个架构上测试这个想法,表明它始终提供性能提升。

英文摘要:

One of the main challenges of deep learning methods is the choice of an appropriate training strategy. In particular, additional steps, such as unsupervised pre-training, have been shown to greatly improve the performances of deep structures. In this article, we propose an extra training step, called post-training, which only optimizes the last layer of the network. We show that this procedure can be analyzed in the context of kernel theory, with the first layers computing an embedding of the data and the last layer a statistical model to solve the task based on this embedding. This step makes sure that the embedding, or representation, of the data is used in the best possible way for the considered task. This idea is then tested on multiple architectures with various data sets, showing that it consistently provides a boost in performance.

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。

↑