文档章节

人工智能资料库:第18辑(20170127)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:22
字数 656
阅读 2
收藏 0
点赞 0
评论 0

  1. 【代码】Sugar Tensor - A slim tensorflow wrapper that provides syntactic sugar for tensor variables

简介:

Sugar Tensor aims to help deep learning researchers/practitioners. It adds some syntactic sugar functions to tensorflow to avoid tedious repetitive tasks. Sugar Tensor was developed under the following principles:

  1. Don't mess up tensorflow. We provide no wrapping classes. Instead, we use a tensor itself so that developers can program freely as before with tensorflow.
  2. Don't mess up the python style. We believe python source codes should look pretty and simple. Practical deep learning codes are very different from those of complex GUI programs. Do we really need inheritance and/or encapsulation in our deep learning code? Instead, we seek for simplicity and readability. For that, we use pure python functions only and avoid class style conventions.

原文链接:https://github.com/buriburisuri/sugartensor


2.【代码】illustration2vec

简介:


illustration2vec (i2v) is a simple library for estimating a set of tags and extracting semantic feature vectors from given illustrations. For details, please seeour project pageorour main paper.

Demo

原文链接:https://github.com/rezoo/illustration2vec


3.【资料】30 Top Videos, Tutorials & Courses on Machine Learning & Artificial Intelligence from 2016

简介:


2016 has been the year of “Machine Learning and Deep Learning”. We have seen the likes of Google, Facebook, Amazon and many more come out in open and acknowledge the impact machine learning and deep learning had on their business.

Last week, I publishedtop videos on deep learning from 2016. I was blown away by the response. I could understand the response to some degree – I found these videos extremely helpful. So, I decided to do a similar article on top videos on machine learning from 2016.

原文链接:https://www.analyticsvidhya.com/blog/2016/12/30-top-videos-tutorials-courses-on-machine-learning-artificial-intelligence-from-2016/?utm_source=feedburner&utm_medium=email&utm_campaign=Feed%3A+AnalyticsVidhya+%28Analytics+Vidhya%29


4.【博客】20+ hottest research papers on Computer Vision, Machine Learning

简介:

Computer Vision used to be cleanly separated into two schools: geometry and recognition. Geometric methods like structure from motion and optical flow usually focus on measuring objective real-world quantities like 3D "real-world" distances directly from images and recognition techniques like support vector machines and probabilistic graphical models traditionally focus on perceiving high-level semantic information (i.e., is this a dog or a table) directly from images.

原文链接:http://www.kdnuggets.com/2016/01/iccv-2015-21-hottest-papers.html


5.【课程】Neural Networks and Deep Learning

简介:

Neural networks have enjoyed several waves of popularity over the past half century. Each time they become popular, they promise to provide a general purpose artificial intelligence--a computer that can learn to do any task that you could program it to do. The first wave of popularity, in the late 1950s, was crushed by theoreticians who proved serious limitations to the techniques of the time. These limitations were overcome by advances that allowed neural networks to discover distributed representations, leading to another wave of enthusiasm in the late 1980s. The second wave died out as more elegant, mathematically principled algorithms were developed (e.g., support-vector machines, Bayesian models). Around 2010, neural nets had a third resurgence. What happened over the past 20 years? Basically, computers got much faster and data sets got much larger, and the algorithms from the 1980s--with a few critical tweaks and improvements--appear to once again be state of the art, consistently winning competitions in computer vision, speech recognition, and natural language processing. Below is a comic strip circa 1990, when neural nets reached public awareness. You might expect to see the same comic today, touting neural nets as the hot new thing, except that now the field has been rechristened deep learning to emphasize the architecture of neural nets that leads to discovery of task-relevant representations.

原文链接:https://www.cs.colorado.edu/~mozer/Teaching/syllabi/DeepLearning2015/


本文转载自:http://www.jianshu.com/p/1d7bcec8a258

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
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
GMIC北京站亮点全揭秘!点击开启你的专属说明书

4月26-28日,GMIC大会将在北京国家会议中心如期举行。本届大会主题为“AI”生万物,谐音爱生万物,届时将有政府官员、人工智能领域科学家、企业家、投资人等各界人士共同出席。 作为全球移动...

Technews科技新报
04/18
0
0
【盘点】2018人工智能机器人大会

AICon全球人工智能与机器学习技术大会 2018(助力人工智能落地) 会议时间:2018-01-13 至 2018-01-14 会议地点:北京 北京国际会议中心 会议网址:https://www.huodongjia.com/event-539998...

活动家会议
2017/12/28
0
0
人工智能有“天花板” 传统产业要“+科技”——知名企业家激战“新经济”

(原标题:人工智能有“天花板” 传统产业要“+科技”——知名企业家激战“新经济”) 中国证券网讯 据新华社12月5日消息,“携手新时代,共话新经济”,第四届世界互联网大会上,多位企业家...

上海证券报·中国证券网
2017/12/05
0
0
AI人工智能很火,但是少了这个市场AI就无法运作

人工智能的大脑 今天是12月3号星期天,明天就要重新开始上班,迎接新的一周。今天AI小编和大家一起来聊聊AI领域的芯片。 AI芯片人工智能时代的大脑,驱动人工智能时代进步的核心要素,目前国...

移动笔记
2017/12/03
0
0
红米 6 vs 红米 6A vs 红米 5 vs 小米 6X 规格比较

红米 6 千元平价手机发布,同场发表比红米 6 更入门的红米 6A。一时之间,红米手机增加 2 名千元的性价比新机,新机自然各方面比上代红米 5 有升级,但红米 6 不再採用 Snapdragon 系列处理器...

小七里外
06/13
0
0
科学家说:AI有加强现存偏见的可能

桑斯坦在《网络共和国》当中提出了算法影响我们的认知世界、并在《信息乌托邦》当中第一次明确提出了算法使人形成“信息茧房”的危害。这是算法对于人脑的影响,而算法应用于人工智能中,也让...

玄学酱
04/13
0
0

没有更多内容

加载失败,请刷新页面

加载更多

下一页

rabbitmq学习记录(三)

工作队列:一个生产者,多个消费者,生产者直接将消息发送到rabbitmq的队列之中 默认采用的是轮询分配:即不管消费者处理信息的效率,队列给所有消费者轮流发送一条信息,直至消息发送完毕 ...

人觉非常君
22分钟前
0
0
Java 之 反射

反射,剖析 Java类 中的 各个组成部分,映射成 一个个 Java对象,多用于 框架和组件,写出复用性高的通用程序。 测试类代码如下: class Person { private String name; public St...

绝世武神
25分钟前
0
0
华为nova3超级慢动作酷玩抖音,没有办法我就是这么强大

华为nova3超级慢动作酷玩抖音,没有办法我就是这么强大!华为nova3超级慢动作酷玩抖音,没有办法我就是这么强大! 在华为最新发布的nova 3手机上,抖音通过华为himedia SDK集成了60fps、超级...

华为终端开放实验室
31分钟前
0
0
多 SSH Key 实现同一台服务器部署多 Git 仓库

本文以以下需求为背景,介绍详细的做法: 需在同一台服务器同时部署两个不同的 Github 仓库(对 Bitbucket 等 git 服务同样适用) root 用户可在远程登录 SSH 后附上预期的 SSH Key 进行 gi...

yeahlife
33分钟前
0
0
003. es6数值的扩展

一、普通扩展 Number 方法,将字符串、数值转为十进制 : Number('0b111') Number.isFinite() 用来检查一个数值是否为有限的:Number.isFinite(15) Number.isNan() 用来检查一个值是否为NaN N...

秋季长青
47分钟前
0
0
C语言数组和指针的语法糖

对于C语言,我可以这样秀:比如当创建一个数组arr[n]之后,一般我们去遍历数组的时候是for (int i = 0; i < n; i++) { a[i]; }但是我知道下表访问符[]是个语法糖,也就是说a[i]在编译器看来是...

ustbgaofan
56分钟前
0
0
Call to undefined function bcmath()的解决方法

乐意黎的ECS主机环境,Centos7.2 + PHP7 由于使用了bcdiv()函数,运行时总在抛错。 Fatal error: Call to undefined function bcmath() in /usr/loca/apache/htdocs/... on line 4 一查得知:......

dragon_tech
今天
0
0
css优先级

..

architect刘源源
今天
0
0
【转】Twitter的分布式自增ID算法snowflake

结构 snowflake的结构如下(每部分用-分开): 0 - 0000000000 0000000000 0000000000 0000000000 0 - 00000 - 00000 - 000000000000 第一位为未使用,接下来的41位为毫秒级时间(41位的长度可以...

talen
今天
0
0
hive支持行级修改

Hive从0.14版本开始支持事务和行级更新,但缺省是不支持的,需要一些附加的配置。要想支持行级insert、update、delete,需要配置Hive支持事务。 一、Hive具有ACID语义事务的使用场景 1. 流式...

hblt-j
今天
0
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