文档章节

人工智能资料库:第12辑(20170120)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:27
字数 1029
阅读 2
收藏 0
点赞 0
评论 0

  1. 【博客】Understanding the new Google Translate

简介:


Google launched a new version of the Translate in September 2016. Since then, there have been a few interesting developments in the project, and this post attempts to explain it all in as simple terms as possible.

The earlier version of the Translate used Phrase-based Machine Translation, or PBMT. What PBMT does is break up an input sentence into a set of words/phrases and translate each one individually. This is obviously not an optimal strategy, since it completely misses out on the context of the overall sentence. The new Translate uses what Google calls *Google Neural Machine Translation (*GNMT**), an improvement over a traditional version of NMT. Lets see how GNMT works on a high-level:

原文链接:https://codesachin.wordpress.com/2017/01/18/understanding-the-new-google-translate/


2.【博客 & 代码】Self-Organizing Maps with Google’s TensorFlow

简介:

A Self-Organizing Map, or SOM, falls under the rare domain of unsupervised learning in Neural Networks. Its essentially a grid of neurons, each denoting one cluster learned during training. Traditionally speaking, there is no concept of neuron ‘locations’ in ANNs. However, in an SOM, each neuron has a location, and neurons that lie close to each other represent clusters with similar properties. Each neuron has a weightage vector, which is equal to the centroid of its particular cluster.

原文链接:https://codesachin.wordpress.com/2015/11/28/self-organizing-maps-with-googles-tensorflow/

原理链接:http://www.ai-junkie.com/ann/som/som1.html


3.【博客】Simple Beginner’s guide to Reinforcement Learning & its implementation

简介:

这篇博客,我近期会把它翻译成中文,并且做一个学习笔记。

One of the most fundamental question for scientists across the globe has been – “How to learn a new skill?”. The desire to understand the answer is obvious – if we can understand this, we can enable human species to do things we might not have thought before. Alternately, we can train machines to do more “human” tasks and create true artificial intelligence.

While we don’t have a complete answer to the above question yet, there are a few things which are clear. Irrespective of the skill, we first learn by interacting with the environment. Whether we are learning to drive a car or whether it an infant learning to walk, the learning is based on the interaction with the environment. Learning from interaction is the foundational underlying concept for all theories of learning and intelligence.

原文链接:https://www.analyticsvidhya.com/blog/2017/01/introduction-to-reinforcement-learning-implementation/


4.【论文】Revisiting Visual Question Answering Baselines

简介:

Visual question answering (VQA) is an interesting learning setting for evaluating the abilities and shortcomings of current systems for image understanding. Many of the recently proposed VQA systems include attention or memory mechanisms designed to support “reasoning”. For multiple-choice VQA, nearly all of these systems train a multi-class classifier on image and question features to predict an answer. This paper questions the value of these common practices and develops a simple alternative model based on binary classification. Instead of treating answers as competing choices, our model receives the answer as input and predicts whether or not an image-question-answer triplet is correct. We evaluate our model on the Visual7W Telling and the VQA Real Multiple Choice tasks, and find that even simple versions of our model perform competitively. Our best model achieves state-of-the-art performance on the Visual7W Telling task and compares surprisingly well with the most complex systems proposed for the VQA Real Multiple Choice task. We explore variants of the model and study its transferability between both datasets. We also present an error analysis of our model that suggests a key problem of current VQA systems lies in the lack of visual grounding of concepts that occur in the questions and answers. Overall, our results suggest that the performance of current VQA systems is not significantly better than that of systems designed to exploit dataset biases.

原文链接:https://arxiv.org/pdf/1606.08390v2.pdf


5.【Tutorial & 代码】Introduction to Natural Language Processing with fastText

简介:

这篇博客,我近期会把它翻译成中文,并且做一个学习笔记。

Natural Language Processing (NLP) is one of the hottest areas in machine learning. Its global purpose is to understand language the way humans do. NLP subareas include machine translation, text classification, speech recognition, sentiment analysis, question answering, text-to-speech, etc.

As in most areas of Machine Learning, NLP accuracy has improved considerably thanks to deep learning. Just to highlight the most recent and impressive achievement, in October 2016 Microsoft Research reached human parity in speech recognition. For that milestone, they used a combination of Convolutional Neural Networks and LSTM networks.

However, not all machine learning is deep learning, and in this notebook I would like to highlight a great example. In the summer of 2016, two interesting NLP papers were published by Facebook Research, Bojanowski et al., 2016 and Joulin et al., 2016. The first one proposed a new method for word embedding and the second one a method for text classification. The authors also opensourced a C++ library with the implementation of these methods, fastText, that rapidly attracted a lot of interest.

The reason for this interest is that fastText obtains an accuracy in text classification almost as good as the state of the art in deep learning, but it is several orders of magnitude faster. In their paper, the authors compare the accuracy and computation time of several datasets with deep nets. As an example, in the Amazon Polarity dataset, fastText achieves an accuracy of 94.6% in 10s. In the same dataset, the crepe CNN model of Zhang and LeCun, 2016 achieves 94.5% in 5 days, while the Very Deep CNN model of Conneau et al., 2016 achieves 95.7% in 7h. The comparison is not even fair, because while fastText's time is computed with CPUs, the CNN models are computed using Tesla K40 GPUs.

原文链接:https://github.com/miguelgfierro/sciblog_support/blob/master/Intro_to_NLP_with_fastText/Intro_to_NLP.ipynb


本文转载自:http://www.jianshu.com/p/ec20a33aa2f2

共有 人打赏支持
AllenOR灵感
粉丝 10
博文 2634
码字总数 82983
作品 0
程序员
预测流行偏好,时尚 AI 未来可望取代造型师

【Technews科技新报】预测时尚潮流是一项需要天分的工作,还得仰赖一个庞大的系统让少数人追捧的时尚进入大众流行市场,进而让业者赚取大笔钞票。现在预测工作也可以交给人工智能,让服饰业者...

黄 嬿
2017/12/26
0
0
人工智能知识整理-第1辑(20170603)-机器学习入门资源汇总

有一天我忽然忘记了一个函数的用法,于是就上谷歌搜,结果搜出来的竟然是自己写的一篇笔记,上面有很详细的回答。当时感觉是跟另外一个自己进行交流,那一个是刚学完知识,印象还非常深的自己...

人工智豪
2017/06/03
0
0
资源 | 剑桥大学:156页PPT全景展示AI过去的12个月(附下载)

  转载自专知   作者:Nathan Benaich、Ian Hogarth      剑桥大学 Nathan Benaich 与 Ian Hogarth 博士共同发布关于人工智能最近 12 个月进展的报告,其中包含对新技术,人才流动,...

机器之心
07/03
0
0
Jetty 9.4.1, Jetty 9.3.16 和 Jetty 9.2.21 发布

Jetty 9.4.1, Jetty 9.3.16 和 Jetty 9.2.21 发布了。 Jetty 是一个开源的 servlet 容器,它为基于 Java 的 web 内容,例如 JSP 和 servlet 提供运行环境。Jetty 是使用 Java 语言编写的,它...

达尔文
2017/01/24
1K
1
人工智能资料库:第72辑(20171203)

1.【会议】Bayesian Deep Learning 简介: While deep learning has been revolutionary for machine learning, most modern deep learning models cannot represent their uncertainty nor......

chen_h
2017/12/03
0
0
人工智能集训营 | AI 时代,未来由你掌控

免费试听时间:第一周课程免费试听 北京时间 4/23 10:00-12:00 美西时间 4/22 19:00-21:00 课程安排:课程为期3个月 北京时间 每周一、四、六、日 10:00-12:00 美西时间 每周日、三、五、六 ...

micf435p6d221ssdld2
04/22
0
0
微软研究院发布开放数据项目,公开内部研究数据集

     编者按:微软技术院士、图灵奖得主Jim Gray提出了科研的第四范式——数据科学在科学研究中的普遍性。随着大数据时代的到来,除了计算机科学领域,其它跨学科与跨领域的研究也同样对...

微软亚洲研究院
06/25
0
0
全球AI芯片榜单:七家中国公司入围Top24

  近日,市场研究公司Compass Intelligence发布了最新研究报告,在全球前15大AI芯片企业排名表中,前三名是英伟达(Nvidia)、英特尔(Intel)以及IBM,华为位列第12名,成为TOP15的中国“独苗...

人工智能技术社区
05/07
0
0
区块链技术让科学家共享患者健康资讯,同时保障个人资料安全

【Technews科技新报】目前医生在依据乳房摄影判断乳癌发生的情况下,有四分之一的乳癌无法被及时判断发现。为了提升乳癌确诊的效率,科学家计划以数百万包含了健康女性以及患有乳癌的女性乳房...

黄 斯沛
04/16
0
0
人工智能时代的工作、学习和生活---《人工智能》阅读笔记

自从“罗辑思维”栏目从优酷网站搬到得到APP并且变为每天几分钟的节目之后,我就很少收听它了。某天,我打开得到APP,并且点开了“罗辑思维”的节目清单,发现有一期的标题包含了“人工智能”...

zhouzxi
2017/07/15
0
0

没有更多内容

加载失败,请刷新页面

加载更多

下一页

shell中的函数、shell中的数组、告警系统需求分析

shell中的函数 格式: 格式: function f_name() { command } 函数必须要放在最前面 示例1(用来打印参数) 示例2(用于定义加法) 示例3(用于显示IP) shell中的数组 shell中的数组1 定义数...

Zhouliang6
今天
2
0
用 Scikit-Learn 和 Pandas 学习线性回归

      对于想深入了解线性回归的童鞋,这里给出一个完整的例子,详细学完这个例子,对用scikit-learn来运行线性回归,评估模型不会有什么问题了。 1. 获取数据,定义问题     没有...

wangxuwei
今天
1
0
MAC安装MAVEN

一:下载maven压缩包(Zip或tar可选),解压压缩包 二:打开终端输入:vim ~/.bash_profile(如果找不到该文件新建一个:touch ./bash_profile) 三:输入i 四:输入maven环境变量配置 MAVEN_HO...

WALK_MAN
今天
0
0
33.iptables备份与恢复 firewalld的9个zone以及操作 service的操作

10.19 iptables规则备份和恢复 10.20 firewalld的9个zone 10.21 firewalld关于zone的操作 10.22 firewalld关于service的操作 10.19 iptables规则备份和恢复: ~1. 保存和备份iptables规则 ~2...

王鑫linux
今天
2
0
大数据教程(2.11):keeperalived+nginx高可用集群搭建教程

上一章节博主为大家介绍了目前大型互联网项目的系统架构体系,相信大家应该注意到其中很重要的一块知识nginx技术,在本节博主将为大家分享nginx的相关技术以及配置过程。 一、nginx相关概念 ...

em_aaron
今天
1
0
Apache Directory Studio连接Weblogic内置LDAP

OBIEE默认使用Weblogic内置LDAP管理用户及组。 要整理已存在的用户及组,此前办法是导出安全数据,文本编辑器打开认证文件,使用正则表达式获取用户及组的信息。 后来想到直接用Apache Dire...

wffger
今天
2
0
HFS

FS,它是一种上传文件的软件。 专为个人用户所设计的 HTTP 档案系统 - Http File Server,如果您觉得架设 FTP Server 太麻烦,那么这个软件可以提供您更方便的档案传输系统,下载后无须安装,...

garkey
今天
1
0
Java IO类库之BufferedInputStream

一、BufferedInputStream介绍 /** * A <code>BufferedInputStream</code> adds * functionality to another input stream-namely, * the ability to buffer the input and to * sup......

老韭菜
今天
0
0
STM 32 窗口看门狗

http://bbs.elecfans.com/jishu_805708_1_1.html https://blog.csdn.net/a1985831055/article/details/77404131...

whoisliang
昨天
1
0
Dubbo解析(六)-服务调用

当dubbo消费方和提供方都发布和引用完成后,第四步就是消费方调用提供方。 还是以dubbo的DemoService举例 -- 提供方<dubbo:application name="demo-provider"/><dubbo:registry address="z...

青离
昨天
2
0

没有更多内容

加载失败,请刷新页面

加载更多

下一页

返回顶部
顶部