20171220-30: 刘晨曦:Progressive Neural Architecture Search

报告嘉宾：刘晨曦（Johns Hopkins University）

报告时间：2017年12月20日（星期三）晚21:00（北京时间）

报告题目：Progressive Neural Architecture Search

主持人：沈为（上海大学）

报告摘要：

We propose a method for learning CNN structures that is more efficient than previous approaches: instead of using reinforcement learning (RL) or genetic algorithms (GA), we use a sequential model-based optimization (SMBO) strategy, in which we search for architectures in order of increasing complexity, while simultaneously learning a surrogate function to guide the search, similar to A* search. On the CIFAR-10 dataset, our method finds a CNN structure with the same classification accuracy (3.41% error rate) as the RL method of Zoph et al. (2017), but 2 times faster (in terms of number of models evaluated). It also outperforms the GA method of Liu et al. (2017), which finds a model with worse performance (3.63% error rate), and takes 5 times longer. Finally we show that the model we learned on CIFAR also works well at the task of ImageNet classification. In particular, we match the state-of-the-art performance of 82.9% top-1 and 96.1% top-5 accuracy.

报告相关文献列表：

Progressive Neural Architecture Search. Chenxi Liu, Barret Zoph, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan Yuille, Jonathan Huang, Kevin Murphy. arXiv preprint arXiv:1712.00559. 2017.

报告人简介：

Chenxi Liu is a third year Ph.D. student at Johns Hopkins University, where he is advised by Bloomberg Distinguished Professor Alan Yuille. Before that, he received M.S. in Statistics at University of California, Los Angeles and B.E. in Automation at Tsinghua University. He has also spent time at Google, Adobe, Toyota Technological Institute at Chicago, University of Toronto, and Rice University. His research lies in computer vision and natural language processing, especially their intersection.

讲者个人主页：http://www.cs.jhu.edu/~cxliu/

特别鸣谢本次Webinar主要组织者：

VOOC责任委员：沈为（上海大学）

VODB协调理事：郑伟诗（中大）

活动参与方式：

1、VALSE Webinar活动全部网上依托VALSE QQ群的“群视频”功能在线进行，活动时讲者会上传PPT或共享屏幕，听众可以看到Slides，听到讲者的语音，并通过文字或语音与讲者交互；

2、为参加活动，需加入VALSE QQ群，目前A、B、C、D、E、F群已满，除讲者等嘉宾外，只能申请加入VALSE G群，群号：669280237。申请加入时需验证姓名、单位和身份，缺一不可。入群后，请实名，姓名身份单位。身份：学校及科研单位人员T；企业研发I；博士D；硕士M

3、为参加活动，请下载安装Windows QQ最新版，群视频不支持非Windows的系统，如Mac，Linux等，手机QQ可以听语音，但不能看视频slides；

4、在活动开始前10分钟左右，主持人会开启群视频，并发送邀请各群群友加入的链接，参加者直接点击进入即可；

5、活动过程中，请勿送花、棒棒糖等道具，也不要说无关话语，以免影响活动正常进行；

6、活动过程中，如出现听不到或看不到视频等问题，建议退出再重新进入，一般都能解决问题；

7、建议务必在速度较快的网络上参加活动，优先采用有线网络连接。