文档章节

人工智能资料库:第14辑(20170123)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:19
字数 748
阅读 3
收藏 0
点赞 0
评论 0

  1. 【代码】Music Auto Tagging Keras

简介:


Music auto-tagging models and trained weights in keras/theano

原文链接:https://github.com/keunwoochoi/music-auto_tagging-keras


2.【论文】Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records

简介:



Secondary use of electronic health records (EHRs) promises to advance clinical research and better inform clinical decision making. Challenges in summarizing and representing patient data prevent widespread practice of predictive modeling using EHRs. Here we present a novel unsupervised deep feature learning method to derive a general-purpose patient representation from EHR data that facilitates clinical predictive modeling. In particular, a three-layer stack of denoising autoencoders was used to capture hierarchical regularities and dependencies in the aggregated EHRs of about 700,000 patients from the Mount Sinai data warehouse. The result is a representation we name “deep patient”. We evaluated this representation as broadly predictive of health states by assessing the probability of patients to develop various diseases. We performed evaluation using 76,214 test patients comprising 78 diseases from diverse clinical domains and temporal windows. Our results significantly outperformed those achieved using representations based on raw EHR data and alternative feature learning strategies. Prediction performance for severe diabetes, schizophrenia, and various cancers were among the top performing. These findings indicate that deep learning applied to EHRs can derive patient representations that offer improved clinical predictions, and could provide a machine learning framework for augmenting clinical decision systems.

原文链接:http://www.nature.com/articles/srep26094


3.【博客】Deriving the Gradient for the Backward Pass of Batch Normalization

简介:

I recently sat down to work on assignment 2 of Stanford’s CS231n. It’s lengthy and definitely a step up from the first assignment, but the insight you gain is tremendous.

Anyway, at one point in the assignment, we were tasked with implementing a Batch Normalization layer in our fully-connected net which required writing a forward and backward pass.

The forward pass is relatively simple since it only requires standardizing the input features (zero mean and unit standard deviation). The backwards pass, on the other hand, is a bit more involved. It can be done in 2 different ways:

  • staged computation: we can break up the function into several parts, derive local gradients for them, and finally multiply them with the chain rule.
  • gradient derivation: basically, you have to do a “pen and paper” derivation of the gradient with respect to the inputs.

It turns out that second option is faster, albeit nastier and after struggling for a few hours, I finally got it to work. This post is mainly a clear summary of the derivation along with my thought process, and I hope it can provide others with the insight and intuition of the chain rule. There is a similar tutorial online already (but I couldn’t follow along very well) so if you want to check it out, head over to Clément Thorey’s Blog.

Finally, I’ve summarized the original research paper and accompanied it with a small numpy implementation which you can view on my Github. With that being said, let’s jump right into the blog.

原文链接:https://kevinzakka.github.io/2016/09/14/batch_normalization/


4.【代码】Visual Debugger for Deep Learning, built on TensorFlow

简介:


TensorDebugger (TDB) is a visual debugger for deep learning. It extends TensorFlow (Google's Deep Learning framework) with breakpoints + real-time visualization of the data flowing through the computational graph.

原文链接:https://github.com/ericjang/tdb


5.【资料】Open Learning

简介:

As a person who does a lot of autonomous learning, the Internet in these days offer a huge amount of possibilities to read/learn about any topic you might think of. There might be more the problem of filtering out useful/good content from the nearly infinite amount of sources. Inspired by a colleague I will try to give a record of whatever I read/saw and can recommend on specific topics. I will also try to add specific links that I have already studied in the past but may help any interested reader (or myself as lookup). Most stuff will be about machine learning in general and more specific about computer vision/image classification as my master thesis is related to these topics. But from time to time I might add also some more fun related topics.

原文链接:http://kratzert.github.io/openlearning.html


本文转载自:http://www.jianshu.com/p/fb86e97b38a0

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
GIAC2017全球互联网架构大会12月在上海举行,最新日程抢先看!

12月22日至23日,多为业界技术大咖将齐聚上海,共同探讨技术变革新趋势。 12月22日至23日,高可用架构和msup联合主办的GIAC 全球互联网架构大会将于上海举行。GIAC 全球互联网架构大会是高可...

行者武松
04/18
0
0
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
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
福利丨吴恩达机器学习新书免费领!

继今年 2 月 Deep Learning Specialization 最后一课上线之后,吴恩达又捡起了之前荒废已久的项目—— Machine Learning Yearning。 这本书此前已经出到了第 14 章,不过因为 Deep Learning ...

r1unw1w
04/11
0
0
CCF-GAIR 2018 第一批包机酒学生名单出炉!AI 科技评论请你来参加CCF-GAIR大会啦!

CCF - GAIR 2018 将于 6 月 29 日 至 7 月 1 日 在深圳举行。 三天议程及强大阵容已经陆续出炉。 6 月 8 日, 雷锋网旗下学术频道 AI 科技评论启动了 CCF-GAIR 2018 的免费门票申请通道, 并...

奕欣
06/16
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
谁说传统企业离人工智能很远?你有一张AI+行业对接大会邀请函

在中国的创新创业大环境下,每年都有新概念的出现,从前几年的“互联网+”到去年的VR热,今年人工智能也成为了投资的热点。 Part I:现象级 在中国的创新创业大环境下,每年都有新概念的出现...

行者武松
02/07
0
0

没有更多内容

加载失败,请刷新页面

加载更多

下一页

【面试题】盲人坐飞机

有100位乘客乘坐飞机,其中有一位是盲人,每位乘客都按自己的座位号就坐。由于盲人看不见自己的座位号,所以他可能会坐错位置,而自己的座位被占的乘客会随便找个座位就坐。问所有乘客都坐对...

garkey
50分钟前
0
0
谈谈神秘的ES6——(二)ES6的变量

谈谈神秘的ES6——(二)ES6的变量 我们在《零基础入门JavaScript》的时候就说过,在ES5里,变量是有弊端的,我们先来回顾一下。 首先,在ES5中,我们所有的变量都是通过关键字var来定义的。...

JandenMa
今天
1
0
arts-week1

Algorithm 594. Longest Harmonious Subsequence - LeetCode 274. H-Index - LeetCode 219. Contains Duplicate II - LeetCode 217. Contains Duplicate - LeetCode 438. Find All Anagrams ......

yysue
今天
0
0
NNS拍卖合约

前言 关于NNS的介绍,这里就不多做描述,相关的信息可以查看NNS的白皮书http://doc.neons.name/zh_CN/latest/nns_background.html。 首先nns中使用的竞价货币是sgas,关于sgas介绍可以戳htt...

红烧飞鱼
今天
1
0
Java IO类库之管道流PipeInputStream与PipeOutputStream

一、java管道流介绍 在java多线程通信中管道通信是一种重要的通信方式,在java中我们通过配套使用管道输出流PipedOutputStream和管道输入流PipedInputStream完成线程间通信。多线程管道通信的...

老韭菜
今天
0
0
用Python绘制红楼梦词云图,竟然发现了这个!

Python在数据分析中越来越受欢迎,已经达到了统计学家对R的喜爱程度,Python的拥护者们当然不会落后于R,开发了一个个好玩的数据分析工具,下面我们来看看如何使用Python,来读红楼梦,绘制小...

猫咪编程
今天
1
0
Java中 发出请求获取别人的数据(阿里云 查询IP归属地)

1.效果 调用阿里云的接口 去定位IP地址 2. 代码 /** * 1. Java中远程调用方法 * http://localhost:8080/mavenssm20180519/invokingUrl.action * @Title: invokingUrl * @Description: * @ret......

Lucky_Me
今天
1
0
protobuf学习笔记

相关文档 Protocol buffers(protobuf)入门简介及性能分析 Protobuf学习 - 入门

OSC_fly
昨天
0
0
Mybaties入门介绍

Mybaties和Hibernate是我们在Java开发中应用的比较多的两个ORM框架。当然,目前Mybaties正在慢慢取代Hibernate,这是因为相比较Hibernate而言Mybaties性能更好,响应更快,更加灵活。我们在开...

王子城
昨天
2
0
编程学习笔记之python深入之装饰器案例及说明文档[图]

编程学习笔记之python深入之装饰器案例及说明文档[图] 装饰器即在不对一个函数体进行任何修改,以及不改变整体的原本意思的情况下,增加函数功能的新函数,因为这个新函数对旧函数进行了装饰...

原创小博客
昨天
1
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