[JAN]Deep transfer learning with joint adaptation networks

        DAN 的作者、清华大学的龙明盛在2017 年机器学习顶级会议ICML 上提出了JAN方法(Joint Adaptation Network),在深度网络中同时进行联合分布的自适应和对抗学习。JAN 方法将只对数据进行自适应的方式推广到了对类别的自适应,提出了JMMD 度量(Joint MMD)。

Abstract

        深度网络已成功地应用于学习可转移(transferable)的特征,以适应模型从源域到不同的目标域的转换。本文提出了联合自适应网络(JAN, joint adaptation networks),该网络基于联合最大平均偏差(JMMD,joint maximum mean discrepancy)准则,通过对多个区域特定层的联合分布进行跨区域对齐来学习迁移网络。采用对抗性训练策略最大化JMMD,使源域和目标域的分布更容易区分。学习可以通过随机梯度下降和反向传播计算的梯度在线性时间进行。实验证明,我们的模型在标准数据集上产生了最先进的结果。

1. Introduction

        在本文中,我们提出联合自适应网络(JAN,joint adaptation networks),通过对多个区域特定层的联合分布进行跨区域对齐来学习迁移网络,实现无监督的领域适应。JAN在很大程度上扩展了深度适应网络DAN(Long et al., 2015)对上述联合分布的推理能力,同时使训练过程更加简单。具体来说,JAN允许一个简单的转换管道,通过卷积神经网络(CNN)处理源域和目标域数据,然后在多个特定任务层对齐激活的联合分布。为了学习参数和实现alignment,,我们提出了联合最大均值差异(JMMD),它衡量源域数据和目标域数据的经验联合分布的核均值embedding 之间的希尔伯特-施密特范数。(which measures the Hilbert-Schmidt norm between kernel mean embedding of empirical joint distributions of source and target data.)

2. Related Work

        主要介绍了Transfer learning的目的、主要技术问题。

4. Joint Adaptation Networks

  • 0
    点赞
  • 4
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Thank you for purchasing the MEAP for Deep Learning with R. If you are looking for a resource to learn about deep learning from scratch and to quickly become able to use this knowledge to solve real-world problems, you have found the right book. Deep Learning with R is meant for statisticians, analysts, engineers and students with a reasonable amount of R experience, but no significant knowledge of machine learning and deep learning. This book is an adaptation of my previously published Deep Learning with Python, with all of the code examples using the R interface to Keras. The goal of the book is to provide a learning resource for the R community that goes all the way from basic theory to advanced practical applications. Deep learning is an immensely rich subfield of machine learning, with powerful applications ranging from machine perception to natural language processing, all the way up to creative AI. Yet, its core concepts are in fact very simple. Deep learning is often presented as shrouded in a certain mystique, with references to algorithms that “work like the brain”, that “think” or “understand”. Reality is however quite far from this science- fiction dream, and I will do my best in these pages to dispel these illusions. I believe that there are no difficult ideas in deep learning, and that’s why I started this book, based on premise that all of the important concepts and applications in this field could be taught to anyone, with very few prerequisites. This book is structured around a series of practical code examples, demonstrating on real- world problems every the notions that gets introduced. I strongly believe in the value of teaching using concrete examples, anchoring theoretical ideas into actual results and tangible code patterns. These examples all rely on Keras, the deep learning library. When I released the initial version of Keras almost two years ago, little did I know that it would quickly skyrocket to become one of the most widely used deep l

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值