<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[dreamweaverccc的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/dreamweaverccc</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; dreamweaverccc]]></copyright><item><title><![CDATA[Docker No Route to Host解决办法]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/107574381</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/107574381</guid><author>dreamweaverccc</author><pubDate>Sat, 25 Jul 2020 10:14:35 +0800</pubDate><description><![CDATA[问题描述:

在服务器上拉了两个docker容器A和B, 容器A用来跑平时实验, 容器B搭了一个postgresql数据库。现想从容器A访问容器B的数据库内容, 在使用psycopg2连接postgresql时, 在主机地址和端口号都正确的条件下, 一直报Docker No Route to Host的错误. 并且, 在本地测试数据库的连接性时, 一直是可以连接的.

解决方案:

主要原因在服务器屏蔽从docker内部的访问, 修改服务器的防火墙设置即可.

(1) 在容器A内输入命令"ifconfig.]]></description><category></category></item><item><title><![CDATA[《Weight Agnostic Neural Networks》（权重无关网络）论文简介]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/100023792</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/100023792</guid><author>dreamweaverccc</author><pubDate>Thu, 29 Aug 2019 17:17:25 +0800</pubDate><description><![CDATA[https://weightagnostic.github.io/


]]></description><category></category></item><item><title><![CDATA[阿里经典推荐论文《Deep Interest Network for Click-Through Rate Prediction》理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/95058983</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/95058983</guid><author>dreamweaverccc</author><pubDate>Mon, 08 Jul 2019 21:48:08 +0800</pubDate><description><![CDATA[Zhou G, Zhu X, Song C, et al. Deep interest network for click-through rate prediction[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery &amp; Data Mining. ACM, 20...]]></description><category></category></item><item><title><![CDATA[经典代码自动生成论文《pix2code: Generating Code from a Graphical User Interface Screenshot》理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/92789011</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/92789011</guid><author>dreamweaverccc</author><pubDate>Wed, 19 Jun 2019 15:16:02 +0800</pubDate><description><![CDATA[Beltramelli T. pix2code: Generating code from a graphical user interface screenshot[C]//Proceedings of the ACM SIGCHI Symposium on Engineering Interactive Computing Systems. ACM, 2018: 3.

一、论文介绍

...]]></description><category></category></item><item><title><![CDATA[One-Shot Video Object Segmentation理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/90374742</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/90374742</guid><author>dreamweaverccc</author><pubDate>Tue, 21 May 2019 13:54:40 +0800</pubDate><description><![CDATA[Caelles S , Maninis K K , Pont-Tuset J , et al. One-Shot Video Object Segmentation[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017.


]]></description><category></category></item><item><title><![CDATA[VOST技术入门了解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/90201365</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/90201365</guid><author>dreamweaverccc</author><pubDate>Tue, 14 May 2019 15:48:41 +0800</pubDate><description><![CDATA[Yao R, Lin G, Xia S, et al. Video Object Segmentation and Tracking: A Survey[J]. arXiv preprint arXiv:1904.09172, 2019.
知乎专栏：深度学习从入门到放弃之CV-video segmentation综述. https://zhuanlan.zhihu.com/p/32247505...]]></description><category></category></item><item><title><![CDATA[Improving Image Captioning with Conditional Generative Adversarial Nets理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89892566</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89892566</guid><author>dreamweaverccc</author><pubDate>Tue, 07 May 2019 17:58:45 +0800</pubDate><description><![CDATA[Chen C , Mu S , Xiao W , et al. Improving Image Captioning with Conditional Generative Adversarial Nets[J]. 2018.

一、前言
1. 基于强化学习的图像标注

]]></description><category></category></item><item><title><![CDATA[Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89518652</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89518652</guid><author>dreamweaverccc</author><pubDate>Fri, 26 Apr 2019 22:44:18 +0800</pubDate><description><![CDATA[Wu M, Mosse M, Goodman N, et al. Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference[J]. arXiv preprint arXiv:1809.01357, 2018.


]]></description><category></category></item><item><title><![CDATA[模式识别与机器学习公式（10.6）推导]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89344206</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89344206</guid><author>dreamweaverccc</author><pubDate>Wed, 17 Apr 2019 15:57:19 +0800</pubDate><description><![CDATA[11

]]></description><category></category></item><item><title><![CDATA[CUDA9深度学习Docker环境Deepo（包含大部分深度学习框架+Jupyter）配置]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89305849</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89305849</guid><author>dreamweaverccc</author><pubDate>Tue, 16 Apr 2019 11:10:10 +0800</pubDate><description><![CDATA[配置前提
安装有docker和nvidia-docker。
配置步骤

下载对应镜像。本配置从中国官方镜像加速上下载。

sudo docker pull registry.docker-cn.com/ufoym/deepo:all-jupyter


]]></description><category></category></item><item><title><![CDATA[BERT论文精读理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89278650</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89278650</guid><author>dreamweaverccc</author><pubDate>Mon, 15 Apr 2019 22:40:04 +0800</pubDate><description><![CDATA[Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018.

该篇论文被评选为2019 NAACL的最佳论文，由Google AI团队在20...]]></description><category></category></item><item><title><![CDATA[EM算法及代码]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89173611</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89173611</guid><author>dreamweaverccc</author><pubDate>Wed, 10 Apr 2019 11:05:54 +0800</pubDate><description><![CDATA[一、算法简介。
EM算法全称为Expectation 	Maximization，即期望极大算法，是一种用于处理含有隐变量（hidden variable）的概率模型参数的极大似然估计，或极大后验概率估计。EM算法是一种迭代算法，每一次迭代可分为两步：E步，求期望（Expectation）；M步，求极大（Maximization）。
二、算法步骤。
引用于PRML。

三、个人总结。
EM算法是求...]]></description><category></category></item><item><title><![CDATA[Graph Neural Networks: A Review of Methods and Applications简介]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89006408</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/89006408</guid><author>dreamweaverccc</author><pubDate>Wed, 10 Apr 2019 08:50:31 +0800</pubDate><description><![CDATA[Jie Zhou et al. 2018.

]]></description><category></category></item><item><title><![CDATA[Progressive Prediction of Student Performance in College Programs理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88866978</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88866978</guid><author>dreamweaverccc</author><pubDate>Wed, 03 Apr 2019 22:18:46 +0800</pubDate><description><![CDATA[Jie Xu, et. al. 2017 AAAI.

]]></description><category></category></item><item><title><![CDATA[机器学习基础]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88902080</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88902080</guid><author>dreamweaverccc</author><pubDate>Sat, 30 Mar 2019 10:33:48 +0800</pubDate><description><![CDATA[Mitchell定义机器学习：对于某类任务T和性能度量P，一个计算机程序被认为可以从经验E中学习是指，通过经验E改进后，它在任务T上由性能度量P衡量的性能有所提升。


...]]></description><category></category></item><item><title><![CDATA[Learning from Semi-Supervised Weak-Label Data理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88812568</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88812568</guid><author>dreamweaverccc</author><pubDate>Tue, 26 Mar 2019 22:05:08 +0800</pubDate><description><![CDATA[Hao-chen Dong, Yu-Feng Li, Zhi-Hua Zhou. 2018 AAAI.
前言
前一阵子读了几篇关于深度学习应用在智慧教育上的论文，对“可解释性”又有了些疑问。于是，这次读了篇使用机器学习方法研究半监督弱标签的论文，换个思路去思考问题。
首先，来看看什么是半监督弱标签问题（semi-supervised weak-label, 以下简称为SSWL）？SSWL是多标签学...]]></description><category></category></item><item><title><![CDATA[Finding Similar Exercises in Online Education Systems理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88706732</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88706732</guid><author>dreamweaverccc</author><pubDate>Fri, 22 Mar 2019 10:06:29 +0800</pubDate><description><![CDATA[Qi Liu, Enhong Chen, et al. 2018 KDD.

]]></description><category></category></item><item><title><![CDATA[Exercise-Enhanced Sequential Modeling for Student Performance Prediction理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88651262</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88651262</guid><author>dreamweaverccc</author><pubDate>Tue, 19 Mar 2019 13:37:47 +0800</pubDate><description><![CDATA[Yu Su, Enhong Chen, et al. 2018 AAAI.

]]></description><category></category></item><item><title><![CDATA[Towards Understanding the Geometry of Knowledge Graph Embeddings理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88592874</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88592874</guid><author>dreamweaverccc</author><pubDate>Sat, 16 Mar 2019 10:12:47 +0800</pubDate><description><![CDATA[Chandrahas et al. 2018 ACL.
论文背景
知识图谱的embedding方式有多种，可按得分函数(score function)的计算表达式分为“加法模型”和“乘法模型”两类（见下图1）。本文提出新的度量指标，研究各种embedding方式的几何(geometry)性质。

图1：知识图谱embedding得分函数分类
度量指标

ATM(alignment to mean)...]]></description><category></category></item><item><title><![CDATA[Bootstrapping Entity Alignment with Knowledge Graph Embedding理解]]></title><link>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88547088</link><guid>https://blog.youkuaiyun.com/dreamweaverccc/article/details/88547088</guid><author>dreamweaverccc</author><pubDate>Thu, 14 Mar 2019 13:29:57 +0800</pubDate><description><![CDATA[Zequn Sun et al. IJCAI 2018.
相关知识介绍

实体对齐(entity alignment)也被称为实体匹配(entity matching)，主要用于消除异构数据中实体冲突、指向不明等不一致性问题，可以从顶层创建一个大规模的统一知识库，从而帮助机器理解多源异质的数据，形成高质量的知识。


Bootstrap是一种统计学上的估计方法，由Stanford统计学的教授Bra...]]></description><category></category></item></channel></rss>