CanChen ggchen@mail.ustc.edu.cn


This is my first day sharing my reading paper and I will try to paraphrase core ideas in these papers with very simple words. Every paper consists three parts, namely, motivation, method, and contribution. In each part, no more than 3 sentences will be used.

 

NAS-Bench-201

  • Motivation:Network search algorithms are often quite expensive and different search spaces also make it difficult for us to compare these algorithms. In fact, we can treat network architectures as X and their corresponding accuracies as Y, and construct a standard dataset to solve this problem.
  • Method: Using cell-based strategy, we only need to find a cell and insert it into the macro structure. In the paper, 4 nodes and 5 operations are used, which means we need to train 15625 cells. As last,the author just trained 15625 models on cifar10,cifar100 and sampled-ImageNet,and provided us with the corresponding training logs.
  • Contribution: The paper is a ICLR paper and is not very novel(at least I think). It shows us again: computing resources is very important. At least, it gives us a benchmark for NAS research and now we can use CPU to do NAS.
 

Peephole

  • Motivation: Can we get the network's performance without training?
  • Method: The author only considers sequential network architectures since we can treat the sequential network architectures as "a language". Then the author uses LSTM to deal with this problem like language modeling.
  • Contribution: The work is kind of limited since it only deals with sequential network architecures while other structures such shortcut paths are in fact dominating this field.
 

Latency-aware

  • Motivation: Current Darts algorithms do not take latency into consideration.
  • Method: First, the author train a regression model that can predict a network's latency based on the network's structure. Then the author inserts this model into bi-level optimization equation as part of the loss function.
  • Contribution: This work is an extension of Darts and can be very useful since latency is important in real scenarios.

PaperReading20200219的更多相关文章

随机推荐

  1. Docker安装、命令详情、层级架构、docker服务启动失败解决方法

    容器背景: 层级架构:  容器对比传统化虚拟机: 可以把docker理解成是一款自带软件(比如:nignx.tomcat.....)的镜像操作系统(首先是要下载镜像) 以下是Windows环境安装Do ...

  2. EF中 GroupJoin 与 Join

    数据: GroupJoin: 返回左表所有数据 using (tempdbEntities context = new tempdbEntities()) { var query = context. ...

  3. Django 实现下载功能时中文文件名问题

    先上最终解决代码(有待验证各浏览器效果): def download_file(request, file_path): file_name = os.path.basename(file_path) ...

  4. Flask - app.debug=True,python manage.py和export FLASK_DEBUG=True,flask run的不同。

    TL;DR,可以直接看下面的总结 问题1:为什么app.config['DEBUG'] = True,然后flask run并没有开启debugger和reloading,而直接运行脚本(python ...

  5. Pychram 运行程序在 run 窗口和 python console 窗口之间切换

    有图有真相 第一步: 第二步:

  6. Java 1.8 红黑树

    红黑树 R-B Tree R-B Tree,全称 Red-Black Tree 又称为 红黑树,它是一种特殊的二叉查找树,红黑树的每个节点都有存储位表示节点的颜色,可以是红Red 或者 黑Black ...

  7. 激活win10企业版,亲测可用,(win7步骤相同,请自行测试)

    其他版本我没试过,亲们可以尝试! win7神key win7神key1:2HYJ4-V71WM-BAF6Y-G2BTH-X8QOD win7神key2:9LM54-Z3LQ1-5IRAN-T4JNI- ...

  8. 关于数据库中的三值逻辑(Tree-Value-Logic)

    在sql中,逻辑表达式(也叫做谓词),可以有三种值:True.False.Unknown,这就是所谓的三值逻辑,,是sql的特有属性. 在大多数编程语言中,逻辑表达式只有两个值,就是True和Fals ...

  9. spring aop @after和@before之类的注解,怎么指定多个切点

    有如下两个切点: @Pointcut("execution(public * com.wyh.data.controller.DepartmentController.*(..))" ...

  10. 一个简单的PHP文件下载方法 download

    <?php /* * *@param function downloadFile 文件下载 * *@param string $filename 下载文件的路径(根目录下的绝对路径) * *@p ...