• Architecture

 
 

 
 

 
 

 
 

  • SemanticCaps

    通过Bi-LSTM表征得到的隐层向量经过multi-head后可以得到R个表征

     
     

     
     

 
 

  • DetectionCaps

    这部分和一般的胶囊网络一样,除了loss function中加入了self attention部分

     
     

     
     

     
     

     
     

     
     

 
 

 
 

  • Zero-shot DetectionCaps

 
 

基本过程和DetectionCaps很相似,计算DetectionCaps中已存在的existing intent和当前inference阶段emerging intent的相似度q,然后加权求和,squash后得到activation vector进行分类

 
 

 
 

 
 

 
 

 
 

 
 

 
 

 
 

 
 

Zero-shot User Intent Detection via Capsule Neural Networks的更多相关文章

  1. 目标检测--Scalable Object Detection using Deep Neural Networks(CVPR 2014)

    Scalable Object Detection using Deep Neural Networks 作者: Dumitru Erhan, Christian Szegedy, Alexander ...

  2. Scalable Object Detection using Deep Neural Networks译文

    原文:https://arxiv.org/abs/1312.2249

  3. 中文版 Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks 摘要 最先进的目标检测网络依靠区域提出算法 ...

  4. tensorfolw配置过程中遇到的一些问题及其解决过程的记录(配置SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving)

    今天看到一篇关于检测的论文<SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real- ...

  5. 【论文笔记】Malware Detection with Deep Neural Network Using Process Behavior

    [论文笔记]Malware Detection with Deep Neural Network Using Process Behavior 论文基本信息 会议: IEEE(2016 IEEE 40 ...

  6. 论文解读(RvNN)《Rumor Detection on Twitter with Tree-structured Recursive Neural Networks》

    论文信息 论文标题:Rumor Detection on Twitter with Tree-structured Recursive Neural Networks论文作者:Jing Ma, Wei ...

  7. [C6] Andrew Ng - Convolutional Neural Networks

    About this Course This course will teach you how to build convolutional neural networks and apply it ...

  8. [C4] Andrew Ng - Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

    About this Course This course will teach you the "magic" of getting deep learning to work ...

  9. [C3] Andrew Ng - Neural Networks and Deep Learning

    About this Course If you want to break into cutting-edge AI, this course will help you do so. Deep l ...

随机推荐

  1. 为什么在 Java 中128==128返回false,而127==127返回true呢?

    为什么在 Java 中128==128返回false,而127==127返回true呢? 有这样一段代码 Integer a=127; Integer b=127; System.out.printl ...

  2. Kubectl操作命令

    Kubectl 自动补全 yum install -y bash-completion source /usr/share/bash-completion/bash_completion $ sour ...

  3. redux有价值的文档

    使用 Redux 管理状态,第 1 部分 https://www.ibm.com/developerworks/cn/web/wa-manage-state-with-redux-p1-david-g ...

  4. Buy Fruits-(构造)

    https://ac.nowcoder.com/acm/contest/847/C 在blueland上有 n n个水果店,它们的编号依次为 0,1,2...n−1 0,1,2...n−1.奇妙的是, ...

  5. kafk设计要点

    kafka的设计目标是高吞吐量,所以kafka自己设计了一套高性能但是不通用的协议,他是仿照AMQP( Advanced Message Queuing Protocol   高级消息队列协议)设计的 ...

  6. 正睿2019省选附加赛 Day10 (这篇其实已经都咕咕了...)

    目录 2019.3.13 A.算算算(二项式定理 斯特林数) B.买买买 C.树树树 2019.3.13 比赛链接 A.算算算(二项式定理 斯特林数) 题目链接 \(x^k\)可以用二项式定理展开,需 ...

  7. NodeJS代码组织与部署

    使用NodeJS编写程序前,为了有个良好的开端,首先需要准备好代码的目录结构和部署方式,就如同修房子要先搭脚手架.本章将介绍与之相关的各种知识. 一.模块路径解析规则 我们已经知道,require函数 ...

  8. nginx之系统参数优化

    系统参数优化 默认的Linux内核参数考虑的是最通用场景,不符合用于支持高并发访问的Web服务器的定义,根据业务特点来进行调整,当Nginx作为静态web内容服务器.反向代理或者提供压缩服务器的服务器 ...

  9. 论文阅读:Single Image Dehazing via Conditional Generative Adversarial Network

    Single Image Dehazing via Conditional Generative Adversarial Network Runde Li∗ Jinshan Pan∗ Zechao L ...

  10. js转义问题

    js转义问题有很多场景,比如常见的根据某个字符串删除或者修改以及将某字符串传递至某个页面. 今天以一个简单的示例代码为例: <html> <head> <meta htt ...