有道翻译WordPress插件新鲜出炉

特色

我自己写的第一个 wordpress 插件,很简单,但很有成就感!

Introduction:

Youdao Translator automatically translates your blog only by move the mouse to choose some words. It supports the following different language pairs:

  • Chinese (Simplified) <-> English
  • Chinese (Simplified) <-&[......]

阅读全文

命令行配置PPTP VPN

图形化界面上配置 VPN 已经很方便了。但是在命令行下,Linux 还不是那么容易能搞定 VPN 的配置已经连接。需要一些软件包的支持和一些配置工作。

下面是基于 Ubuntu 的配置步骤。假定你的 VPN 服务器地址是 1.1.1.1,账号是 vpn,密码是 vpn

  • 安装软件包

sudo yum install pptp pptp-setup

  • 创建名为 vpnclient 的配置文件

sudo pptpsetup –create vpnclient –server 1.1.1.1 –username vpn –password vpn

该命令就[......]

阅读全文

互联网世界的“人工智能”——探秘“深度学习”的前世今生

本周一,加利福尼亚州的Lake Tahoe。Facebook CEO Mark Zuckerburg造访了神经信息处理系统(Neutral Information Processing Systems, 下文简称NIPS)举办的“深度学习研讨会”(Deep Learning Workshop)。Zuckerburg在研讨会上宣布,纽约大学数据科学中心的Yann LeCun教授将兼任Facebook人工智能实验室(Artificial Intelligence Lab, AI Lab)的主管。[......]

阅读全文

人脸识别新技术准确率超99%:比肉眼更加精准

        转载自:新浪科技

http://static.cnbetacdn.com/newsimg/2014/0623/25_1jFS0hrCb.jpg        在此之前,汤晓鸥的研究组开发了一个基于高斯过程的人脸识别技术GaussianFace (高斯脸),取得了98.52%的识别率。这也是计算机自动识别算法的识别率首次超过肉眼

        DeepID将GaussianFace的人脸识别世界纪录又向前推进了一个台阶,首次超过99%的LFW识别率。

        人脸识别是计算机视觉和人工智能研究领域一个重要挑战,在公共安全、执法、移动互联网和娱乐领域都有大量应用。它也成为检验人工智能是否可以在解决某些特定智能问题上达到甚至超越人的重要测试基准。

        汤晓鸥的研究组在人脸识别[......]

阅读全文

自然语言处理和统计机器翻译的著名研究机构

爱丁堡大学:http://www.statmt.org/ued/

斯坦福大学:http://nlp.stanford.edu/projects/mt.shtml

Google Research:http://research.google.com/pubs/NaturalLanguageProcessing.html

Microsoft Research:http://research.microsoft.com/en-us/groups/nlphttp://research.microsoft.com/en-us/groups/nlc/

SMT Rese[......]

阅读全文

比较OpenBLAS,Intel MKL和Eigen的矩阵相乘性能

对于机器学习的很多问题来说,计算的瓶颈往往在于大规模以及频繁的矩阵运算,主要在于以下两方面:

(Dense/Sparse) Matrix – Vector product
(Dense/Sparse) Matrix – Dense Matrix product
如何使机器学习算法运行更高效摆在我们面前,很多人都会在代码中直接采用一个比较成熟的矩阵运算数学库,面对繁多的数学库,选择一个合适的库往往会令人头疼,这既跟你的运算环境有关,也跟你的运算需求有关,不是每个库都能完胜的。

这篇文章的主要目的就是比较几个常见的BLAS库的矩阵运算性能,分别是[......]

阅读全文

LightSide’s Top Ten Papers at ACL 2013

ACL wraps up today. Here’s my rundown of what was most exciting at this year’s conference.

Let me start off by describing my bias: my Ph.D. research was in conversational discourse analysis, focusing on social behaviors in language. I also wrote LightSIDE, the open source tool for feature extraction, machine learning model building, and in-depth error analysis for text data. Since I left Carnegie Mellon, I’ve been focusing on automated writing evaluation, with applications to both essay grading and generation of formative feedback directly to students.

Because of this background, I spent very little time paying attention to machine translation talks. I don’t have the mathematics background to really contribute to discussions of parsing or machine learning optimization papers. I spent most sessions in the talks on social behaviors, dialogue, and some of the more creative fields, like summarization and generation. I also really like off-kilter applications of NLP, and growing fields like digital humanities.

My criteria was that the paper was full of innovative ideas and applicable to real world problems; I care less about accuracy numbers and pushing the diminishing returns on well-known corpora and tasks. With that being said, here’s my top 10 papers from this year’s conference.[......]

阅读全文