Machine Learning Week_1 Introduction 1-4

目录

• 1 Introduction
  • 1.1 Video: Welcome
    • unfamiliar words
    • symbols
  • 1.2 Video: What is machine learning?
    • unfamiliar words
  • 1.3 Reading: What is Machine Learning?
  • 1.4 Reading: How to Use Discussion Forums
    • Upvoting Posts
    • Report Abuse
    • Following
    • Improving Your Posts
    • unfamiliar words

I remember that the CET-4 teacher told us that it was good to see the English interpretation. I have been trying this, but the interpretation of the same language is downward, that is, a more basic concept, which makes it difficult for us to understand what a word means. The interpretation of different languages is horizontal. We can clearly understand what another language says.

My experience is to have a look at both.

At the same time, add English examples.

1 Introduction

• Video: Welcome
• Video: What is Machine Learning?
• Reading: What is Machine Learning?
• Reading: How to Use Discussion Forums?
• Video: Supervised Learning
• Reading: Supervised Learning
• Video: Unsupervised Learning
• Reading: Unsupervised Learning
• Reading: Who are Mentors?
• Reading: Get to Know Your Classmates
• Reading: Frequently Asked Questions

1.1 Video: Welcome

Welcome to this free online class on machine learning.

Machine learning is one of the most exciting recent technologies. And in this class, you learn about the state of the art and also gain practice implementing and deploying these algorithms yourself.

You've probably use a learning algorithm dozens of times a day without knowing it. Every time you use a web search engine like Google or Bing to search the internet, one of the reasons that works so well is because a learning algorithm, one implemented by Google or Microsoft, has learned how to rank web pages.

Every time you use Facebook or Apple's photo typing application and it recognizes your friends' photos, that's also machine learning. Every time you read your email and your spam filter saves you from having to wade through tons of spam email, that's also a learning algorithm.

For me one of the reasons I'm excited is the AI dream of someday building machines as intelligent as you or me. We're a long way away from that goal, but many AI researchers believe that the best way to towards that goal is through learning algorithms that try to mimic how the human brain learns. I'll tell you a little bit about that too in this class.

In this class you learn about state-of-the-art machine learning algorithms. But it turns out just knowing the algorithms and knowing the math isn't that much good if you don't also know how to actually get this stuff to work on problems that you care about. So, we've also spent a lot of time developing exercises for you to implement each of these algorithms and see how they work fot yourself.

So why is machine learning so prevalent today?

It turns out that machine learning is a field that had grown out of the field of AI, or artificial intelligence. We wanted to build intelligent machines and it turns out that there are a few basic things that we could program a machine to do such as how to find the shortest path from A to B. But for the most part we just did not know how to write AI programs to do the more interesting things such as web search or photo tagging or email anti-spam.

There was a realization that the only way to do these things was to have a machine learn to do it by itself. So, machine learning was developed as a new capability for computers and today it touches many segments of industry and basic science.

For me, I work on machine learning and in a typical week I might end up talking to helicopter pilots, Computational biologists, a bunch of computer systems people (so my colleagues here at Stanford) and averaging two or three times a week I get email from people in industry from Silicon Valley contacting me who have an interest in applying learning algorithms to their own problems.

This is a sign of the range of problems that machine learning touches. There is autonomous robotics, computational biology, tons of things in Silicon Valley that machine learning is having an impact on.

Here are some other examples of machine learning. There's database mining. One of the reasons machine learning has so pervaded is the growth of the web and the growth of automation. All this means that we have much larger data sets than ever before.

So, for example tons of Silicon Valley companies are today collecting web click data, also called clickstream data, and are trying to use machine learning algorithms to mine this data to understand the users better and to serve the users better, that's a huge segment of Silicon Valley right now.

Medical records. With the advent of automation, we now have electronic medical records, so if we can turn medical records into medical knowledge, then we can start to understand disease better.

Computational biology. With automation again, biologists are collecting lots of data about gene sequences, DNA sequences, and so on, and machines running algorithms are giving us a much better understanding of the human genome, and what it means to be human.

And in engineering as well, in all fields of engineering, we have larger and larger, and larger and larger data sets, that we're trying to understand using learning algorithms.

A second range of machinery applications is ones that we cannot program by hand. So for example, I've worked on autonomous helicopters for many years. We just did not know how to write a computer program to make this helicopter fly by itself. The only thing that worked was having a computer learn by itself how to fly this helicopter.

Handwriting recognition. It turns out one of the reasons it's so inexpensive today to route a piece of mail across the countries, in the US and internationally, is that when you write an envelope like this, it turns out there's a learning algorithm that has learned how to read your handwriting so that it can automatically route this envelope on its way, and so it costs us a few cents to send this thing thousands of miles.

And in fact if you've seen the fields of natural language processing or computer vision, these are the fields of AI pertaining to understanding language or understanding images. Most of natural language processing and most of computer vision today is applied machine learning.

Learning algorithms are also widely used for self-customizing programs. Every time you go to Amazon or Netflix or iTunes Genius, and it recommends the movies or products and music to you, that's a learning algorithm. If you think about it they have million users; there is no way to write a million different programs for your million users. The only way to have software give these customized recommendations is to become learn by itself to customize itself to your preferences.

Finally learning algorithms are being used today to understand human learning and to understand the brain. We'll talk about how researches are using this to make progress towards the big AI dream.

A few months ago, a student showed me an article on the top twelve IT skills. The skills that information technology hiring managers cannot say no to. It was a slightly older article, but at the top of this list of the twelve most desirable IT skills was machine learning.

Here at Stanford, the number of recruiters that contact me asking if I know any graduating machine learning students is far larger than the machine learning students we graduate each year. So I think there is a vast, unfulfilled demand for this skill set, and this is a great time to be learning about machine learning, and I hope to teach you a lot about machine learning in this class.

In the next video, we'll start to give a more formal definition of what is machine learning. And we'll begin to talk about the main types of machine learning problems and algorithms.

You'll pick up some of the main machine learning terminology, and start to get a sense of what are the different algorithms, and when each one might be appropriate.

unfamiliar words

1. the state of the art： 最新的技术

2. deploy [dɪˈplɔɪ] v. 调用，有效利用。
   exp: V to move soldiers or weapons into a position where they are ready for military action

   • 2 000 troops were deployed in the area.
     那个地区部署了2 000人的部队。
   • The president said he had no intention of deploying ground troops.
     总统称并不打算部署地面部队。

3. wade 英 [weɪd] v. 跋涉，涉，蹚（水或淤泥等）
   exp: V to walk with an effort through sth, especially water or mud

   • He waded into the water to push the boat out

4. prevalent 英 [ˈprevələnt] adj. 普遍的，广泛的
   exp: ADJ that exists or is very common at a particular time or in a particular place

   • a prevalent view
     普遍的观点

5. turn out 出现结果 out 外面 出来

6. anti-spam 反垃圾邮件

7. realization 英 [ˌriːəlaɪˈzeɪʃn] n. 认识 实现 意识到

   • There is a growing realization that changes must be made.
     越来越多的人认识到改革势在必行。

8. segment 英 [ˈseɡmənt] n. 部分，片段

   • She cleaned a small segment of the painting.
     她擦干净了这幅画的一小部分。

9. typical [ˈtɪpɪkl] adj. 典型的

   • a typical Italian cafe 典型的意大利式小餐馆

10. helicopter [ˈhelɪkɑːptər] n. 直升机

    • a helicopter pilot 直升机驾驶员 pilot [ˈpaɪlət]

11. autonomous [ɔːˈtɑːnəməs] adj. 自主的;自治的;

    • an autonomous republic/state/province
      自治共和国 / 州 / 省

12. mining [ˈmaɪnɪŋ] n. 采矿

    • Mining can be costly in terms of lives.
      采矿有时会造成重大的生命损失。

13. mine [maɪn] n. 矿井 v. 采矿

14. pervade [pərˈveɪd] vt. 弥漫;
    exp: VT to spread through and be noticeable in every part of sth

    • The entire house was pervaded by a sour smell. entire [ɪnˈtaɪər]
      整所房子都充满了酸味。

15. advent [ˈædvent] n. 重要事件、人物、发明等的）出现，到来
    exp: N the coming of an important event, person, invention, etc.

    • the advent of new technology
      新技术的出现

16. genome [ˈdʒiːnoʊm] n. 基因组;染色体组

    • the human genome
      人体基因组

17. machinery [məˈʃiːnəri] n. 大型机械

    • agricultural/industrial machinery
      农业 / 工业机械

18. envelope [ˈenvəloʊp] n. 信封
    exp: N a flat paper container used for sending letters in

    • writing paper and envelopes
      信纸和信封

19. pertain [pəˈteɪn] pertaining [pərˈteɪnɪŋ] 与…相关；属于；适用（于）
    exp：VERB If one thing pertains to another, it relates, belongs, or applies to it

    • Those laws no longer pertain.
      那些法律已不适用了。

20. customize [ˈkʌstəmaɪz] vn. 订制，订做，改制（以满足顾主的需要）
    exp: V to make or change sth to suit the needs of the owner

    • You can customize the software in several ways.
      你可用几种方法按需要编制这个软件。

21. recruiter [rɪˈkrutər] recruiters [rɪˈkrutərz] n. 招聘人员

    • Few recruiters would interview you without the language ability.
      如果不具备语言能力，很少有雇主会给你面试机会。

22. vast [væst] adj.辽阔的；巨大的；庞大的；大量的
    exp：ADJ extremely large in area, size, amount, etc.

    • a vast area of forest
      莽莽苍苍的森林

23. Silicon Valley [ˌsɪlɪkən ˈvæli] n. 硅谷

24. biologists [baɪˈɒlədʒɪsts] n. 生物学家

25. definition [ˌdefɪˈnɪʃn] n. 定义

26. automatically [ˌɔtəˈmætɪkli]

symbols

• [ʊ]
  foot [fʊt] put [pʊt] good [ɡʊd]

• [uː]
  goose [ɡuːs] two [tuː] blue [bluː]

• [ʌ]
  strut [strʌt] mud [mʌd] love [lʌv] blood [mʌd]

• [ɑː]
  father [ˈfɑːðər] start [stɑːt] hard [hɑːd]

• [ɒ]
  lot 英 [lɒt] 美 [lɑːt]
  odd 英 [ɒd] 美 [ɑːd]
  wash 英 [wɒʃ] 美 [wɑːʃ]

• [ɔː]
  thought [θɔːt] law [lɔː] north [nɔːθ] war [wɔː(r)]

1.2 Video: What is machine learning?

What is machine learning? In this video, we will try to define what it is and also try to give you a sense of when you want to use machine learning. Even among machine learning practitioners, there isn't a well accepted definition of what is and what isn't machine learning. But let me show you a couple of examples of the ways that people have tried to define it. Here's a definition of what is machine learning as due to Arthur Samuel. He defined machine learning as the field of study that gives computers the ability to learn without being explicitly learned.

Samuel's claim to fame was that back in the 1950, he wrote a checkers playing program and the amazing thing about this checkers playing program was that Arthur Samuel himself wasn't a very good checkers player. But what he did was he had to programmed maybe tens of thousands of games against himself, and by watching what sorts of board positions tended to lead to wins and what sort of board positions tended to lead to losses, the checkers playing program learned over time what are good board positions and what are bad board positions. And eventually learn to play checkers better than the Arthur Samuel himself was able to. This was a remarkable result. Arthur Samuel himself turns out not to be a very good checkers player. But because a computer has the patience to play tens of thousands of games against itself, no human has the patience to play that many games. By doing this, a computer was able to get so much checkers playing experience that it eventually became a better checkers player than Arthur himself.

This is a somewhat informal definition and an older one. Here's a slightly more recent definition by Tom Mitchell who's a friend of Carnegie Melon. So Tom defines machine learning by saying that a well posed learning problem is defined as follows. He says, a computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E. I actually think he came out with this definition just to make it rhyme. For the checkers playing examples, the experience E would be the experience of having the program play tens of thousands of games itself. The task T would be the task of playing checkers, and the performance measure P will be the probability that wins the next game of checkers against some new opponent.

Throughout these videos, besides me trying to teach you stuff, I'll occasionally ask you a question to make sure you understand the content.

Here's one.

On top is a definition of machine learning by Tom Mitchell. Let's say your email program watches which emails you do or do not mark as spam. So in an email client like this, you might click the Spam button to report some email as spam but not other emails. And based on which emails you mark as spam, say your email program learns better how to filter spam email. What is the task T in this setting? In a few seconds, the video will pause and when it does so, you can use your mouse to select one of these four radio buttons to let me know which of these four you think is the right answer to this question.

So hopefully you got that this is the right answer, classifying emails is the task T. In fact, this definition defines a task T performance measure P and some experience E. And so, watching you label emails as spam or not spam, this would be the experience E and and the fraction of emails correctly classified, that might be a performance measure P. And so on the task of systems performance, on the performance measure P will improve after the experience E.

In this class, I hope to teach you about various different types of learning algorithms. There are several different types of learning algorithms.The main two types are what we call supervised learning and unsupervised learning. I'll define what these terms mean more in the next couple videos. It turns out that in supervised learning, the idea is we're going to teach the computer how to do something. Whereas in unsupervised learning, we're going to let it learn by itself. Don't worry if these two terms don't make sense yet.

In the next two videos, I'm going to say exactly what these two types of learning are. You might also hear other ghost terms such as reinforcement learning and recommender systems. These are other types of machine learning algorithms that we'll talk about later. But the two most use types of learning algorithms are probably supervised learning and unsupervised learning. And I'll define them in the next two videos and we'll spend most of this class talking about these two types of learning algorithms.

It turns out what are the other things to spend a lot of time on in this class is practical advice for applying learning algorithms. This is something that I feel pretty strongly about. And exactly something that I don't know if any other university teachers. Teaching about learning algorithms is like giving a set of tools. And equally important or more important than giving you the tools as they teach you how to apply these tools. I like to make an analogy to learning to become a carpenter. Imagine that someone is teaching you how to be a carpenter, and they say, here's a hammer, here's a screwdriver, here's a saw, good luck. Well, that's no good. You have all these tools but the more important thing is to learn how to use these tools properly.

There's a huge difference between people that know how to use these machine learning algorithms, versus people that don't know how to use these tools well. Here, in Silicon Valley where I live, when I go visit different companies even at the top Silicon Valley companies, very often I see people trying to apply machine learning algorithms to some problem and sometimes they have been going at for six months. But sometimes when I look at what their doing, I say, I could have told them like, gee, I could have told you six months ago that you should be taking a learning algorithm and applying it in like the slightly modified way and your chance of success will have been much higher.

So what we're going to do in this class is actually spend a lot of the time talking about how if you're actually trying to develop a machine learning system, how to make those best practices type decisions about the way in which you build your system. So that when you're finally learning algorithim, you're less likely to end up one of those people who end up persuing something after six months that someone else could have figured out just a waste of time for six months.

So I'm actually going to spend a lot of time teaching you those sorts of best practices in machine learning and AI and how to get the stuff to work and how the best people do it in Silicon Valley and around the world. I hope to make you one of the best people in knowing how to design and build serious machine learning and AI systems. So that's machine learning, and these are the main topics I hope to teach.

In the next video, I'm going to define what is supervised learning and after that what is unsupervised learning. And also time to talk about when you would use each of them.

unfamiliar words

1. practitioner [prækˈtɪʃənər] n. 专业人员
   exp: N a person who works in a profession, especially medicine or law

2. experience [ɪkˈspɪriəns]

3. throughout [θruːˈaʊt] prep. 各处；遍及 自始至终；贯穿整个时期

   • exp1: PREP in or into every part of sth
     They export their products to markets throughout the world.
     他们把产品出口到世界各地的市场。

   • exp2:PREP during the whole period of time of sth
     The museum is open daily throughout the year.
     这个博物馆一年到头每天都开放。

4. occasionally [əˈkeɪʒnəli] adv. 偶然；偶尔；有时候
   exp: ADV sometimes but not often
   We occasionally meet for a drink after work.
   我们下班后偶尔相聚小酌。

5. fraction [ˈfrækʃn] n. 小部分；少量；一点儿 分数 a/b

   • exp1: N a small part or amount of sth
     Only a small fraction of a bank's total deposits will be withdrawn at any one time.
     任何时候，一家银行的总存款只有少量会被提取。
   • exp2: N a division of a number, for example ⅝

6. analogy [əˈnælədʒi] n. 类比；比喻
   exp: N a comparison of one thing with another thing that has similar features; a feature that is similar

   • The teacher drew an analogy between the human heart and a pump.
     老师打了个比喻，把人的心脏比作水泵。

7. carpenter [ˈkɑːpəntə(r)] n. 木匠

   • He was a carpenter by trade.
     他以木工为业。

1.3 Reading: What is Machine Learning?

Two definitions of Machine Learning are offered. Arthur Samuel described it as: "the field of study that gives computers the ability to learn without being explicitly programmed." This is an older, informal definition.

Tom Mitchell provides a more modern definition: "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E."

Example: playing checkers.

E = the experience of playing many games of checkers

T = the task of playing checkers.

P = the probability that the program will win the next game.

In general, any machine learning problem can be assigned to one of two broad classifications:

Supervised learning and Unsupervised learning.

1.4 Reading: How to Use Discussion Forums

Upvoting Posts

When you enter the discussion forum for your course, you will see an Upvote button under each post. We encourage you to upvote posts you find thoughtful, interesting, or helpful. This is the best way to ensure that quality posts will be seen by other learners in the course. Upvoting will also increase the likelihood that important questions get addressed and answered.

Report Abuse

• Coursera's Code of Conduct prohibits:

• Bullying or threatening other users

• Posting spam or promotional content

• Posting mature content

• Posting assignment solutions (or other violations of the Honor Code)

Please report any posts that infringe upon copyright or are abusive, offensive, or that otherwise violate Coursera’s Honor Code by using the Report this option found under the menu arrow to the right of each post.

Following

If you find a particular thread interesting, click the Follow button under the original post of that thread page. When you follow a post, you will receive an email notification anytime a new post is made.

Improving Your Posts

Course discussion forums are your chance to interact with thousands of like-minded individuals around the world. Getting their attention is one way to do well in this course. In any social interaction, certain rules of etiquette are expected and contribute to more enjoyable and productive communication.

The following are tips for interacting in this course via the forums, adapted from guidelines originally compiled by AHA! and Chuq Von Rospach & Gene Spafford:

1. Stay on topic in existing forums and threads. Off-topic posts make it hard for other learners to find information they need. Post in the most appropriate forum for your topic, and do not post the same thing in multiple forums.

2. Use the filters at the top of the forum page (Latest, Top, and Unanswered) to find active, interesting content.

3. Upvote posts that are helpful and interesting.

4. Be civil. If you disagree, explain your position with respect and refrain from any and all personal attacks.

5. Stay on topic. In particular, don’t change the subject in the middle of an existing thread – just start a new topic.

6. Make sure you’re understood, even by non-native English speakers. Try to write full sentences, and avoid text-message abbreviations or slang. Be careful when you use humor and sarcasm as these messages are easy to misinterpret.

7. If asking a question, provide as much information as possible, what you’ve already considered, what you’ve already read, etc.

8. Cite appropriate references when using someone else’s ideas, thoughts, or words.

9. Do not use a forum to promote your product, service, or business.

10. Conclude posts by inviting other learners to extend the discussion. For example, you could say “I would love to understand what others think.”

11. Do not post personal information about other posters in the forum.

12. Report spammers.

For more details, refer to Coursera's Forum Code of Conduct

https://learner.coursera.help/hc/en-us/articles/208280036-Coursera-Code-of-Conduct.

These tips and tools for interacting in this course via the forums were adapted from guidelines originally by The University of Illinois.

unfamiliar words

1. Upvoting 向上投票

2. likelihood [ˈlaɪklihʊd] n. likely 可能的 + hood 性质 → 可能性
   exp: N the chance of sth happening; how likely sth is to happen
   There is very little likelihood of that happening.
   几乎没有发生那种事情的可能.

3. Conduct [kənˈdʌkt] n. 行为 v. 表现 实施；执行

   • The sport has a strict code of conduct (N).
     体育运动有严格的行为规范。

   • exp: V to behave in a particular way
     He conducted himself far better than expected.
     他表现得比预料的要好得多。

   • exp2: V to organize and/or do a particular activity
     to conduct an experiment/an inquiry/a survey
     进行实验 / 询问 / 调查

4. Report Abuse 报告辱骂行为;报告滥用

5. Bully [ˈbʊli] Bullying [ˈbʊliɪŋ] v. 欺辱

   • My son is being bullied at school.
     我儿子在学校里受欺负。

6. promotional [prəˈməʊʃənl] adj. 发广告的 宣传的

7. mature [məˈtʃʊr] n. 成熟的 成人的

8. assignment [əˈsaɪnmənt] n. 任务

   • You will need to complete three written assignments per semester.
     你每学期要完成三个书面作业。

9. violations [ˌvaɪəˈleɪʃənz] violation [ˌvaɪə'leɪʃ(ə)n] n. 违反

10. infringe [ɪnˈfrɪndʒ] v. 违背，触犯
    exp: V to break a law or rule

    • The material can be copied without infringing copyright.
      这份材料可以复制，不会侵犯版权。

11. arrow [ˈærəʊ] n.箭;箭号;箭头

12. thread [θred] n. 线 互联网的消息

13. interact [ˌɪntərˈækt] vi. 互动;相互作用; 沟通交流
    exp: V to communicate with sb, especially while you work, play or spend time with them

    • Teachers have a limited amount of time to interact with each child.
      教师和每个孩子沟通的时间有限。

14. like-minded [ˌlaɪk ˈmaɪndɪd] adj. 想法相同的；志趣相投的

    • the opportunity to mix with hundreds of like-minded people.
      与许许多多志趣相投的人交流的机会

15. etiquette [ˈetɪket] n. 礼仪;(社会或行业中的)礼节;规矩

    • medical/legal/professional etiquette
      医学界的 / 法律界的 / 行业规矩

16. productive [prəˈdʌktɪv] adj. 有效益的；富有成效的
    exp1: ADJ doing or achieving a lot

    • a productive meeting
      有成效的会议

17. civil [ˈsɪvl] adj.有礼貌的；客气的 民众的

    • a civil court
      民事法庭

18. refrain [rɪˈfreɪn] 克制；节制；避免
    exp: V to stop yourself from doing sth, especially sth that you want to do

    • Please refrain from smoking.
      请勿吸烟。

19. abbreviation [əˌbriviˈeɪʃən] abbreviations [əˌbriviˈeɪʃəns] n. 缩略语

20. slang [slæŋ] n. 俚语

    • Archie liked to think he kept up with current slang.
      阿奇喜欢那种紧跟潮流，讲满口时髦新词的感觉。

21. sarcasm 英 [ˈsɑːkæzəm] 美 [ˈsɑːrkæzəm] n.讽刺;嘲讽;挖苦
    tips：sarc 肉 + asm 情况，现象 → 尖刻的话像咬掉人一块肉一样 → 尖刻讽刺

    • 'What a pity,' Graham said with a hint of sarcasm...
      “太遗憾了，”格雷厄姆略带挖苦地说道。

22. misinterpret [ˌmɪsɪnˈtɜːprət] vt.曲解;误解;误释
    exp: VT to understand sth/sb wrongly

    • His comments were misinterpreted as a criticism of the project.
      他的评论被误解为对这个项目的批评。

23. cite [saɪt] v. 提及（原因）；举出 引用
    exp: VN to mention sth as a reason or an example, or in order to support what you are saying

    • He cited his heavy workload as the reason for his breakdown.
      他说繁重的工作负荷是导致他累垮的原因。

24. The University of Illinois 美国伊利诺斯大学