PaperReading20200219
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
- 运维数据同步工具:rsync,serync,csync,drbd,info(基于文件系统)
Rsync官方站点:http://rsync.samba.org 1. Rsync rsync是一款开源的实现数据全量与增量同步备份的工具 生产环境中使用的场景: 1:一般用于数据异地备份 2:用于 ...
- hadoop学习笔记(一):NameNade持久化和DataNode概念
其中的fsimage 称为时点备份,又叫磁盘镜像快照,这个是NameNode的一个 持久化的方式之一:缺点,在内存数据序列化的时候比较慢 具体的过程:因为我们所知道的NameNode一般是存储在内存中 ...
- Windows server 2012 R2 服务器用户自动锁定
开启共享文件夹后,发现经常会自动锁定导致,共享用户无法正常访问共享文件夹(原因不明) 解决办法,打开本地安全策略 把账户锁定阈值改为0
- C# MD5加密-MD5Helper
原文地址:https://ken.io/note/csharp-md5 一.前言 MD5说明http://zh.wikipedia.org/wiki/MD5 .NET MD5类 官方文档&示例 ...
- Python 输入与输出
Python2版本 raw_input raw_input("输入提示"),会把输入的内容当做字符串返回 input 会把用户输入的内容当做代码来处理,可以理解为 raw_inpu ...
- pywinauto教程
转:pywinauto教程https://blog.csdn.net/weixin_40161673/article/details/83246861 ** 一.环境安装**1.命令行安装方法pip ...
- MAC系统 - 系统目录结构
版权声明:本文为博主原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明.本文链接:https://blog.csdn.net/smstong/article/detai ...
- 深入JAVA注解-Annotation(学习过程)
JAVA注解-Annotation学习 本文目的:项目开发过程中遇到自定义注解,想要弄清楚其原理,但是自己的基础知识不足以支撑自己去探索此问题,所以先记录问题,然后补充基础知识,然后解决其问题.记录此 ...
- [python]python中的一些包以及他们的基本用处和安装
pika可以用来连接rabbitmqpip install pika -i http://pypi.douban.com/simple/ --trusted-host pypi.douban.com ...
- WEB - JSONP
JSON with Padding参考 https://zh.wikipedia.org/wiki/JSONP http://www.runoob.com/json/json-jsonp.html 使 ...