HIERARCHICAL REPRESENTATIONS FOR EFFICIENT ARCHITECTURE SEARCH

Hanxiao Liu∗
Carnegie Mellon University
hanxiaol@cs.cmu.edu
Karen Simonyan, Oriol Vinyals, Chrisantha Fernando, Koray Kavukcuoglu
DeepMind
{simonyan,vinyals,chrisantha,korayk}@google.com
ABSTRACT
We explore efficient neural architecture search methods and present a simple yet
powerful evolutionary algorithm that can discover new architectures achieving
state of the art results. Our approach combines a novel hierarchical genetic representation
scheme that imitates the modularized design pattern commonly adopted
by human experts, and an expressive search space that supports complex topologies.
Our algorithm efficiently discovers architectures that outperform a large
number of manually designed models for image classification, obtaining top-1 error
of 3.6% on CIFAR-10 and 20.3% when transferred to ImageNet, which is competitive
with the best existing neural architecture search approaches and represents
the new state of the art for evolutionary strategies on this task. We also present
results using random search, achieving 0.3% less top-1 accuracy on CIFAR-10
and 0.1% less on ImageNet whilst reducing the architecture search time from 36
hours down to 1 hour.

最后编辑于
©著作权归作者所有,转载或内容合作请联系作者
平台声明:文章内容(如有图片或视频亦包括在内)由作者上传并发布,文章内容仅代表作者本人观点,简书系信息发布平台,仅提供信息存储服务。

推荐阅读更多精彩内容

  • “学霸”的正确姿势是什么?不怕麻烦,以及可以提出好问题的能力。提好问题的能力就是先解决无数的小问题之后,实在解决不...
    穆建园阅读 1,716评论 0 0
  • 做了一个梦 恍恍惚惚的下楼,去楼下找算命的 算命先生一副很专业的样子,闭着眼睛,掐着手指,坐在那里。我走过去,坐下...
    七荷阅读 4,196评论 0 2
  • 入选时间:2017年5月日 入选级别:第七层融会贯通 入选理由:【濟】从春,一名普通的教师,两个孩子的父亲。在面对...
    周助人阅读 2,415评论 0 1
  • 想写一句话或者一段话的时候就往这里添。 有了简书,再也不怕写作时网页奔溃了! { I was a writer, ...
    Cyberpunk阅读 786评论 0 1