文档章节

人工智能资料库:第28辑(20170209)

AllenOR灵感
 AllenOR灵感
发布于 2017/09/10 01:23
字数 603
阅读 2
收藏 0

  1. 【博客】Using Apache Spark for large-scale language model training

简介:

Processing large-scale data is at the heart of what the data infrastructure group does at Facebook. Over the years we have seen tremendous growth in our analytics needs, and to satisfy those needs we either have to design and build a new system or adopt an existing open source solution and improve it so it works at our scale.

For some of our batch-processing use cases we decided to use Apache Spark, a fast-growing open source data processing platform with the ability to scale with a large amount of data and support for custom user applications.

原文链接:https://code.facebook.com/posts/678403995666478/using-apache-spark-for-large-scale-language-model-training/


2.【论文】Deep Successor Reinforcement Learning

简介:

Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components – a reward predictor and a successor map. The successor map represents the expected future state occupancy from any given state and the reward predictor maps states to scalar rewards. The value function of a state can be computed as the inner product between the successor map and the reward weights. In this paper, we present DSR, which generalizes SR within an end-to-end deep reinforcement learning framework. DSR has several appealing properties including: increased sensitivity to distal reward changes due to factorization of reward and world dynamics, and the ability to extract bottleneck states (subgoals) given successor maps trained under a random policy. We show the efficacy of our approach on two diverse environments given raw pixel observations – simple grid-world domains (MazeBase) and the Doom game engine. 2

原文链接:https://arxiv.org/pdf/1606.02396.pdf


3.【博客】Lets practice Backpropagation

简介:

In the previous post we went through a system of nested nodes and analysed the update rules for the system.We also went through the intuitive notion of backpropagation and figured out that it is nothing but applying chain rule over and over again.Initially for this post I was looking to apply backpropagation to neural networks but then I felt some practice of chain rule in complex systems would not hurt.So,in this post we will apply backpropogation to systems with complex functions so that the reader gets comfortable with chain rule and its applications to complex systems.

原文链接:https://jasdeep06.github.io/posts/Lets-practice-backpropagation/


4.【博客】Deep Learning in R

简介:

Deep learning is a recent trend in machine learning that models highly non-linear representations of data. In the past years, deep learning has gained a tremendous momentum and prevalence for a variety of applications (Wikipedia 2016a). Among these are image and speech recognition, driverless cars, natural language processing and many more. Interestingly, the majority of mathematical concepts for deep learning have been known for decades. However, it is only through several recent developments that the full potential of deep learning has been unleashed (Nair and Hinton 2010; Srivastava et al. 2014).

原文链接:http://www.rblog.uni-freiburg.de/2017/02/07/deep-learning-in-r/


5.【代码】Practical PyTorch tutorials, focused on using RNNs for NLP

简介:


Learn PyTorch with project-based tutorials. So far they are focused on applying recurrent neural networks to natural language tasks.

These tutorials aim to:

  • Acheive specific goals with minimal parts
  • Demonstrate modern techniques with common data
  • Use low level but low complexity models
  • Reach for readablity over efficiency

原文链接:https://github.com/spro/practical-pytorch


本文转载自:http://www.jianshu.com/p/6f706584d7b7

共有 人打赏支持
AllenOR灵感
粉丝 11
博文 2635
码字总数 83001
作品 0
程序员
私信 提问
【Java每日一题】20170209

20170208问题解析请点击今日问题下方的“【Java每日一题】20170209”查看(问题解析在公众号首发,公众号ID:weknow619) 今日问题: 请问主程序输出结果是什么?(点击以下“【Java每日一题...

weknow
2017/02/09
0
0
【Java每日一题】20170210

20170209问题解析请点击今日问题下方的“【Java每日一题】20170210”查看(问题解析在公众号首发,公众号ID:weknow619) 今日问题: 请问主程序输出结果是什么?(点击以下“【Java每日一题...

weknow
2017/02/10
0
0
免费教材丨第48期:业界大牛中文教学视频《深度学习:进阶》第25-28讲

小编说 我们将继续发放彭老师的《深度学习:进阶》课程,本期发放第25-28讲,本教材由麦子学院提供,现表示感谢。本教学视频为中文教学,代码讲解为主,通俗易懂哦! 彭亮简介 美国犹他州立大...

r1unw1w
2017/10/29
0
0
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

没有更多内容

加载失败,请刷新页面

加载更多

大数据教程(11.9)hive操作基础知识

上一篇博客分享了hive的简介和初体验,本节博主将继续分享一些hive的操作的基础知识。 DDL操作 (1)创建表 #建表语法CREATE [EXTERNAL] TABLE [IF NOT EXISTS] table_name [(col_name ...

em_aaron
今天
2
0
OSChina 周四乱弹 —— 我家猫真会后空翻

Osc乱弹歌单(2019)请戳(这里) 【今日歌曲】 @我没有抓狂 :#今天听这个# 我艇牛逼,百听不厌,太好听辣 分享 Led Zeppelin 的歌曲《Stairway To Heaven》 《Stairway To Heaven》- Led Z...

小小编辑
今天
2
0
node调用dll

先安装python2.7 安装node-gyp cnpm install node-gyp -g 新建一个Electron-vue项目(案例用Electron-vue) vue init simulatedgreg/electron-vue my-project 安装electron-rebuild cnpm ins......

Chason-洪
今天
3
0
scala学习(一)

学习Spark之前需要学习Scala。 参考学习的书籍:快学Scala

柠檬果过
今天
3
0
通俗易懂解释网络工程中的技术,如STP,HSRP等

导读 在面试时,比如被问到HSRP的主备切换时间时多久,STP几个状态的停留时间,自己知道有这些东西,但在工作中不会经常用到,就老是记不住,觉得可能还是自己基础不够牢固,知识掌握不够全面...

问题终结者
昨天
4
0

没有更多内容

加载失败,请刷新页面

加载更多

返回顶部
顶部