Problem: time series classification

shallow RNNs: the first layer splits the input sequence and runs several independent RNNs.  The second layer consumes the output of the first layer to capture long dependencies.

We improve inference time over standard RNNs without compromising accuracy.

Time series -------- temporal dependencies. Sequential models such as RNN are particularly well-suited in this context.

Directly leveraging RNNs for prediction in constrained scenarios is challenging, and requires large training and inference costs.

?? how long the recurrence of RNN should be?

Each time series is divided into independent parts, and a shared RNN operates on each brick independently, thus ensuring a small model size and short recurrence.

Only has a short recurrence.

Supplementary knowledge:

1. theoretical justification

2. weak/ strong assumptions; Model flow:

  • assumption/ environment ~ weak or strong
  • model
  • results
  • evaluation ~ baseline or indicator.

3. Sequential models: RNN;

PP: Shallow RNNs: a method for accurate time-series classification on tiny devices的更多相关文章

  1. PP: Triple-shapelet networks for time series classification

    Problem: time series classification shapelet-based method: two issues 1. for multi-class imbalanced ...

  2. PP: Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data

    From: Stanford University; Jure Leskovec, citation 6w+; Problem: subsequence clustering. Challenging ...

  3. PP: Extracting statisticla graph features for accurate and efficient time series classification

    Problem: TSC, time series classification; Traditional TSC: find global similarities or local pattern ...

  4. Paper: A novel method for forecasting time series based on fuzzy logic and visibility graph

    Problem Forecasting time series. Other methods' drawback: even though existing methods (exponential ...

  5. PP: Multilevel wavelet decomposition network for interpretable time series analysis

    Problem: the important frequency information is lack of effective modelling. ?? what is frequency in ...

  6. Shallow copy and Deep copy

    Shallow copy and Deep copy 第一部分: 一.来自wikipidia的解释: Shallow copy One method of copying an object is t ...

  7. System and method for assigning a message

    A processor of a plurality of processors includes a processor core and a message manager. The messag ...

  8. ICLR 2014 International Conference on Learning Representations深度学习论文papers

    ICLR 2014 International Conference on Learning Representations Apr 14 - 16, 2014, Banff, Canada Work ...

  9. 计算机视觉code与软件

    Research Code A rational methodology for lossy compression - REWIC is a software-based implementatio ...

随机推荐

  1. 关系模式范式分解教程 3NF与BCNF口诀

    https://blog.csdn.net/sumaliqinghua/article/details/86246762 [通俗易懂]关系模式范式分解教程 3NF与BCNF口诀!小白也能看懂原创置顶 ...

  2. centos7使用fdisk:创建和维护MBR分区表

    1.在VMware选择要添加硬盘的虚拟机,添加一块硬盘. 这样就有两块硬盘 2.重启虚拟机. cd /dev #dev是设备目录,下面有很多很多设备,其中就包含硬盘 ll grep | sd #过滤s ...

  3. ssh远程连接到Ubuntu

    1.ubuntu首先得安装ssh sudo apt-get install openssh-server 2.启动ssh sudo /etc/init.d/ssh start 3.检查是否开启 ps ...

  4. 测试.NET core MiddleWare 运行逻辑

    话不多说,直接开整. 首先创建一个.NET CORE web 工程,创建完成之后,会自动创建相关文件如图(本示例基于.NET CORE 3.0): 打开Startup.cs可以看到在Configure ...

  5. 使用SignalR从服务端主动推送警报日志到各种终端(桌面、移动、网页)

    微信公众号:Dotnet9,网站:Dotnet9,问题或建议:请网站留言, 如果对您有所帮助:欢迎赞赏. 使用SignalR从服务端主动推送警报日志到各种终端(桌面.移动.网页) 阅读导航 本文背景 ...

  6. Java 8 Stream Api 中的 peek 操作

    1. 前言 我在Java8 Stream API 详细使用指南[1] 中讲述了 [Java 8 Stream API]( "Java 8 Stream API") 中 map 操作 ...

  7. 爬取漫画DB上的《浪客行》

    漫画链接:https://www.manhuadb.com/manhua/324 建议:早上爬,速度较快. 天下无双宫本武藏 代码 # https://www.manhuadb.com/manhua/ ...

  8. day7 基础数据类型&集合&深浅拷贝

    基础数据类型汇总: #!/usr/bin/env python # -*- coding:utf-8 -*- ''' str int ''' # str s = ' a' print(s.isspac ...

  9. Jenkins+robotframework持续集成环境(一)

    一.安装JDK 系统环境:CentOS Linux release 7.3.1611 x86_64 GNU/Linux Jenkins是基于Java开发的持续集成系统(CI),所以运行环境必须安装JD ...

  10. Mybatis的延迟加载和立即加载

    Mybatis的延迟加载和立即加载 示例:在一对多中,当我们有一个用户,他有100个帐户 问题1:在查询用户时,要不要把关联的账户查出来? 问题2:在查询账户时,要不要把关联的用户信息查出来? 问题1 ...