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 10
博文 2634
码字总数 82983
作品 0
程序员
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
柯洁又一次输了人机大战:不敌国产AI 直言太无力

▼ 点击上方蓝字 关注网易智能 为你解读AI领域大公司大事件,新观点新应用 【网易智能讯 4月28日消息】昨日,第一届“吴清源杯”世界女子围棋赛暨2018世界人工智能围棋大赛在福州举行,中国知...

mcil9g4065q
04/28
0
0
【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
依图夺脸部辨识首奖,施密特:美国 AI 优势只剩 5 年

Thomson Reuters 28 日报导,根据美国智库“新美国安全中心”(CNAS)专家 Elsa Kania 发布的报告,中国在科技领域已经不比美国差,可能已有能力在人工智能(AI)项目超越美国。 Alphabet I...

moneydj
2017/11/29
0
0

没有更多内容

加载失败,请刷新页面

加载更多

WinDbg

参考来自:http://www.cnit.net.cn/?id=225 SRV*C:\Symbols*http://msdl.microsoft.com/download/symbols ctrl + d to open dump_file Microsoft (R) Windows Debugger Version 6.12.0002.633......

xueyuse0012
36分钟前
2
0
OSChina 周五乱弹 —— 想不想把92年的萝莉退货

Osc乱弹歌单(2018)请戳(这里) 【今日歌曲】 @罗马的王:分享松澤由美的单曲《地球ぎ》 很久没看圣斗士星矢了 《地球ぎ》- 松澤由美 手机党少年们想听歌,请使劲儿戳(这里) @开源中国首...

小小编辑
今天
11
1
springBoot条件配置

本篇介绍下,如何通过springboot的条件配置,控制Bean的创建 介绍下开发环境 JDK版本1.8 springboot版本是1.5.2 开发工具为 intellij idea(2018.2) 开发环境为 15款MacBook Pro 前言 很多时候,...

贺小五
今天
1
0
javascript source map 的使用

之前发现VS.NET会为压缩的js文添加一个与文件名同名的.map文件,一直没有搞懂他是用来做什么的,直接删除掉运行时浏览器又会报错,后来google了一直才真正搞懂了这个小小的map文件背后的巨大...

粒子数反转
昨天
1
0
谈谈如何学Linux和它在如今社会的影响

昨天,还在农耕脑力社会,今天已经人工智能技术、大数据、信息技术的科技社会了,高速开展并迅速浸透到当今科技社会的各个方面,Linux日益成为人们信息时代的到来,更加考验我们对信息的处理程...

linux-tao
昨天
1
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