文档章节

人工智能资料库:第17辑(20170126)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:20
字数 784
阅读 1
收藏 0
点赞 0
评论 0

  1. 【代码】Pre-trained word vectors of 30+ languages

简介:

This project has two purposes. First of all, I'd like to share some of my experience in nlp tasks such as segmentation or word vectors. The other, which is more important, is that probably some people are searching for pre-trained word vector models for non-English languages. Alas! English has gained much more attention than any other languages has done. Check this to see how easily you can get a variety of pre-trained English word vectors without efforts. I think it's time to turn our eyes to a multi language version of this.

原文链接:https://github.com/Kyubyong/wordvectors?utm_content=buffer71c26&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer


2.【博客 & 代码】RNNs in Tensorflow, a Practical Guide and Undocumented Features

简介:

In a previous tutorial series I went over some of the theory behind Recurrent Neural Networks (RNNs) and the implementation of a simple RNN from scratch. That’s a useful exercise, but in practice we use libraries like Tensorflow with high-level primitives for dealing with RNNs.

With that using an RNN should be as easy as calling a function, right? Unfortunately that’s not quite the case. In this post I want to go over some of the best practices for working with RNNs in Tensorflow, especially the functionality that isn’t well documented on the official site.

原文链接:https://opendatascience.com/blog/rnns-in-tensorflow-a-practical-guide-and-undocumented-features/?+Data+Science+Newsletter&utm_term=0_2ea92bb125-f4ea9cc60f-245860601


3.【书】A Course in Machine Learning

简介:

Machine learning is the study of algorithms that learn from data and experience. It is applied in a vast variety of application areas, from medicine to advertising, from military to pedestrian. Any area in which you need to make sense of data is a potential consumer of machine learning.

CIML is a set of introductory materials that covers most major aspects of modern machine learning (supervised learning, unsupervised learning, large margin methods, probabilistic modeling, learning theory, etc.). It's focus is on broad applications with a rigorous backbone. A subset can be used for an undergraduate course; a graduate course could probably cover the entire material and then some.

原文链接:http://ciml.info/#chapters


4.【论文 & 代码】Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences

简介:

Recurrent Neural Networks (RNNs) have become the state-of-the-art choice for extracting patterns from temporal sequences. However, current RNN models are ill-suited to process irregularly sampled data triggered by events generated in continuous time by sensors or other neurons. Such data can occur, for example, when the input comes from novel event-driven artificial sensors that generate sparse, asynchronous streams of events or from multiple conventional sensors with different update intervals. In this work, we introduce the Phased LSTM model, which extends the LSTM unit by adding a new time gate. This gate is controlled by a parametrized oscillation with a frequency range that produces updates of the memory cell only during a small percentage of the cycle. Even with the sparse updates imposed by the oscillation, the Phased LSTM network achieves faster convergence than regular LSTMs on tasks which require learning of long sequences. The model naturally integrates inputs from sensors of arbitrary sampling rates, thereby opening new areas of investigation for processing asynchronous sensory events that carry timing information. It also greatly improves the performance of LSTMs in standard RNN applications, and does so with an order-of-magnitude fewer computes at runtime.

原文链接:https://arxiv.org/pdf/1610.09513v1.pdf

代码链接:https://github.com/Enny1991/PLSTM


5.【论文 & 代码】WaveNet: A Generative Model for Raw Audio

简介:


This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. The model is fully probabilistic and autoregressive, with the predictive distribution for each audio sample conditioned on all previous ones; nonetheless we show that it can be efficiently trained on data with tens of thousands of samples per second of audio. When applied to text-to-speech, it yields state-ofthe-art performance, with human listeners rating it as significantly more natural sounding than the best parametric and concatenative systems for both English and Mandarin. A single WaveNet can capture the characteristics of many different speakers with equal fidelity, and can switch between them by conditioning on the speaker identity. When trained to model music, we find that it generates novel and often highly realistic musical fragments. We also show that it can be employed as a discriminative model, returning promising results for phoneme recognition.

原文链接:https://arxiv.org/pdf/1609.03499v2.pdf

代码链接:https://github.com/buriburisuri/speech-to-text-wavenet


本文转载自:http://www.jianshu.com/p/b043a74317c9

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
世界智能大会本周即将开幕,17个国家、1800多位人工智能专家莅临

雷锋网(公众号:雷锋网)消息:由国家发展和改革委员会、科学技术部、工业和信息化部、国家互联网信息办公室、中国科学院、中国工程院、中国科学技术协会、天津市人民政府等单位主办,第二届世...

camel
05/14
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
哈工大成立人工智能研究院,NLP全国前三

哈工大 20 年代校址(来源:哈工大官网) 作者 | 阿司匹林 出品 | AI科技大本营(公众号ID:rgznai100) 今日(5 月 5 日),哈尔滨工业大学正式宣布成立人工智能研究院,王亚东教授担任首任...

dqcfkyqdxym3f8rb0
05/05
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
中国AI崛起,独角兽深兰科技亮相3E北京国际人工智能大会

本次大会以“智动全球,慧聚未来”为主题,共同展现人类科技智能技术的最新进展。 无人便利店、无人驾驶、人机交互对话、智能家居、AI医疗…… 如今,人工智能已成为引领科技发展的重要驱动力...

行者武松
04/10
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
【今日AI】12月13日

【1分钟AI】 1、智联招聘:中国AI人才需求半年升3倍 月薪3.5万人才缺口大 2、高通携手网易游戏 预计2018年推出首款VR游戏 3、交通也玩区块链 中国交通运输链在广州成立 4、亚马逊研究员开发出...

Yetta000
2017/12/13
0
0

没有更多内容

加载失败,请刷新页面

加载更多

下一页

JPA @MappedSuperclass 注解说明

基于代码复用和模型分离的思想,在项目开发中使用JPA的@MappedSuperclass注解将实体类的多个属性分别封装到不同的非实体类中。 1.@MappedSuperclass注解只能标准在类上:@Target({java.lang....

海博1600
6分钟前
0
0
Scala Configuration 相关API

Play使用了 Typesafe config library,但是也提供了一个有着更多Scala高级特性的的 Configuration 封装。不熟悉Typesafe配置的开发者可以移步 configuration文件的语法和特性文档。 读取配置...

Landas
今天
1
0
使用cookie技术 记住账号

1. 效果 2. 实现过程 2.1 前端 将用户的选中传递给后台 这个参数的获取是 参考:https://my.oschina.net/springMVCAndspring/blog/1860498 // var rememberLogin = $("#rememberLoginId").i...

Lucky_Me
今天
1
0
《趣谈网络协议》02之网络分层的真实含义

一、提出问题 1.提出问题 当你听到什么二层设备、三层设备、四层 LB 和七层 LB 中层的时候,是否有点一头雾水,不知道这些所谓的层,对应的各种协议具体要做什么“工作”? 2.这四个问题你弄...

aibinxiao
今天
2
0
Python3学习日志二 Python中的集合set和字典dict

1.集合set 定义一个集合set 我们可以看到定义集合set有两种不同的形式,如果要定义一个空的集合set不能用{}而是要用set();另外,集合是无序的,而且set中的元素是不可重复的,如果你定义了一...

Mr_bullshit
今天
0
0
adb 操作指令详解

ADB,即 Android Debug Bridge,它是 Android 开发/测试人员不可替代的强大工具,也是 Android 设备玩家的好玩具。 注:有部分命令的支持情况可能与 Android 系统版本及定制 ROM 的实现有关。...

孟飞阳
今天
0
0
nodejs安装以及环境配置(很好的node安装和配置文章,少走很多弯路)

一、安装环境 1、本机系统:Windows 10 Pro(64位) 2、Node.js:v6.9.2LTS(64位) 二、安装Node.js步骤 1、下载对应你系统的Node.js版本:https://nodejs.org/en/download/ 2、选安装目录进...

sprouting
今天
1
0
Redisson

了解了Redisson,发现使用挺简单的,接下来准备深入学习一下。 Redisson介绍 Redisson是架设于Redis基础之上的一个Java驻内存数据网格(In-Memory Data Grid) Redisson在基于NIO的Netty框架上...

to_ln
今天
0
0
python有哪些好玩的应用实现,用python爬虫做一个二维码生成器

python爬虫不止可以批量下载数据,还可以有很多有趣的应用,之前也发过很多,比如天气预报实时查询、cmd版的实时翻译、快速浏览论坛热门帖等等,这些都可以算是爬虫的另一个应用方向! 今天给...

python玩家
今天
0
0
python爬虫日志(3)-爬去异步加载网页

在浏览器检查元素页面中,选取Network中的XHR选项即可观察每次加载页面,网页发出的请求,观察url的规律即可利用封装的函数对每一页进行爬取。

茫羽行
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