前言

最近开始读《Deep Learning》一书。这让我有了一个边读书边写笔记的动机:能够让人很轻松流畅的把握住这本书的脉络,从而读懂这本书的核心内容。
由于终究是英文表达更地道,因此该笔记都是节选自书中的原文。只有在我比较有把握的情况下才会给个别概念加上中文翻译。另外,“个人总结”部分是我自己的总结。各位读者如果有建议或意见,欢迎留言。谢谢!

Deep Learning Chapter 1 Introduction

Concept Chinese Description
Artificial Intelligence (AI) 人工智能 Intelligent software to automate routine labor, understand speech or images, make diagnoses in medicine and support basic scientific research.
Machine Learning 机器学习 AI systems acquire their own knowledge by extracting patterns from raw data.
Representation Learning 表示学习 Use machine learning to discover not only the mapping from representation to output but also the representation itself.
AI Deep Learning AI 深度学习 Computers learn from experience and understand the world in terms of a hierarchy of concepts.

In the early days of AI, the field rapidly tackled and solved problems that are intellectually difficult for human beings but relatively straightforward for computers — problems that can be described by a list of formal (形式化), mathematical rules.
Reason: Abstract and formal tasks that are among the most difficult mental undertakings for a human being are among the easiest for a computer.

Challenge to AI: Problems that human solve intuitively, but hard to describe formally.
Example: Recognizing spoken words or faces in images.
Key challenge: How to get informal (非形式化) knowledge into a computer.
A solution: Machine learning.

Challenge to simple machine learning: The performance of simple machine learning algorithms depends heavily on the representation of the data they are given.
Key challenge: What features should be extracted. Feature (特征): The piece of information included in the representation.
A solution: Representation learning.

Goal of representation learning: To separate the factors of variation that explain the observed data. Factors: Sources of influence, can be thought of as concepts or abstractions that help us make sense of the rich variability of the data.

Challenge to representation learning: Disentangle the factors of variation and discard the ones that we do not care about.
A solution: Deep learning.

Method: Introducing representations that are expressed in terms of other, simpler representations.

Two main ways of measuring the depth of a mode:
1. The depth of the computational graph.
2. the depth of the graph describing how concepts are related to each other. It is used by deep probabilistic models,

个人总结

概念 输入 输出
Simple machine Learning 特征 最终结果
Representation Learning 原始数据 特征
Deep Learning 原始数据 多层次特征,就像一棵树,上一层特征是下一层特征的抽象。下一层特征更简单。

Deep Learning Notes: Chapter 1 Introduction相关推荐

  1. 机器学习(Machine Learning)深度学习(Deep Learning)资料(Chapter 2)

    机器学习(Machine Learning)&深度学习(Deep Learning)资料(Chapter 2) - tony的专栏 - 博客频道 - CSDN.NET 注:机器学习资料篇目一共 ...

  2. 李菲菲课程笔记:Deep Learning for Computer Vision – Introduction to Convolution Neural Networks

    转载自:http://www.analyticsvidhya.com/blog/2016/04/deep-learning-computer-vision-introduction-convoluti ...

  3. 机器学习----(Machine Learning)深度学习(Deep Learning)资料(Chapter 1)

    文章转至:作者:yf210yf  感谢您提供的资源 资料汇总的很多,转载一下也方便自己以后慢慢学习 注:机器学习资料篇目一共500条,篇目二开始更新 希望转载的朋友,你可以不用联系我.但是一定要保留原 ...

  4. 机器学习(Machine Learning)深度学习(Deep Learning)资料(Chapter 1

    <Brief History of Machine Learning> 介绍:这是一篇介绍机器学习历史的文章,介绍很全面,从感知机.神经网络.决策树.SVM.Adaboost到随机森林.D ...

  5. 【译】Distributed Deep Learning - Part 1 - An Introduction

    注意:同时,我发表了关于并行梯度下降的硕士论文 ,该论文提供了对下述概念的完整和更详细的描述. 在以下博文中,我们研究分布式深度学习的主题,或者更确切地说,如何使用数据并行方法来并行化梯度下降. 我们 ...

  6. 【深度学习Deep Learning】资料大全

    感谢关注天善智能,走好数据之路↑↑↑ 欢迎关注天善智能,我们是专注于商业智能BI,人工智能AI,大数据分析与挖掘领域的垂直社区,学习,问答.求职一站式搞定! 对商业智能BI.大数据分析挖掘.机器学习, ...

  7. 机器学习(Machine Learning)深度学习(Deep Learning)资料汇总

    本文来源:https://github.com/ty4z2008/Qix/blob/master/dl.md 机器学习(Machine Learning)&深度学习(Deep Learning ...

  8. 深度学习Deep Learning 资料大全

    转自:http://www.cnblogs.com/charlotte77/ [深度学习Deep Learning]资料大全 最近在学深度学习相关的东西,在网上搜集到了一些不错的资料,现在汇总一下: ...

  9. 深度学习(deep learning)--资料大全

    最近在学深度学习相关的东西,在网上搜集到了一些不错的资料,现在汇总一下: Free Online Books Deep Learning66 by Yoshua Bengio, Ian Goodfel ...

  10. (转)机器学习(Machine Learning)深度学习(Deep Learning)资料

    原文链接:https://github.com/ty4z2008/Qix/blob/master/dl.md 机器学习(Machine Learning)&深度学习(Deep Learning ...

最新文章

  1. 15 分钟搭建一个基于XLNET的文本分类模型——keras实战
  2. 12.MapReduce第2部分(WordCount词频统计、自然连接)
  3. Arthas-MathGame
  4. quartz集群分布式(并发)部署解决方案-Spring
  5. java笔记_2020年java程序员、java工程师必备资料(内含java学习思维图、视频教程、源码笔记等)...
  6. Java图形编程实验总结_实验二java图形界面编程2015级.doc
  7. Ehcache整合spring配置
  8. IATF16949:2016汽车质量管理体系认证办理流程
  9. COPRA RF 2005 SR1最新版 (冷弯成型,轧辊设计)
  10. 八皇后问题(启发式搜索)
  11. php mysql后台管理模板_[开源]TP6后台管理模板
  12. TPshop项目介绍
  13. Unity3d之表情动画--眨眼
  14. python使用to_csv(mode=‘a‘)追加数据/(mode=‘w‘)覆盖文件数据
  15. Loadrunner场景设计之场景计划
  16. Electron桌面应用打包流程详情
  17. 解决树莓派4B无线鼠标迟滞/延迟的问题
  18. 21年双非二战南京大学软件学院专硕经验贴
  19. Clickhouse副本与分片
  20. 局域网ip地址不够用-增加内网IP地址

热门文章

  1. ASP.NET文件的上传与下载
  2. VS2010与.NET4系列 13. ASP.NET 4 SEO 改进
  3. 地震日记-2008-05-14
  4. 郁闷!我的Gmail邮箱的问题!
  5. 报错Caused by: org.hibernate.AnnotationException: No identifier specified for entity: com.liuyanzhao.b
  6. pandas df中有几个数组_还在抱怨pandas运行速度慢?这几个方法会颠覆你的看法
  7. Python(八):条件与循环
  8. 【CF-gym101889:B】Buggy ICPC(找规律+思维)
  9. 【POJ2104】K-th Number(区间第k小的数---主席树模版题+离散化)
  10. 驰为vi10旗舰版linux,驰为Vi10平板电脑完全安装Win10步骤 BY Chinasred