In this video, you learn the definition of what it is, and also get a sense of when you might want to apply it.

在本視頻中，您將瞭解它的定義，並瞭解何時需要應用它。

Let's take a look together.

讓我們一起來看看。

Here's a definition of what is machine learning that is attributed to Arthur Samuel.

以下是亞瑟-塞繆爾對機器學習的定義。

He defined machine learning as the field of study that gives computers the ability to learn without being exclusively programmed.

他將機器學習定義為一個研究領域，它賦予計算機學習能力，而無需專門編程。

Samuel's claim to fame was that back in the 1950s, he wrote the checkers playing program.

塞繆爾的成名作是他在 20 世紀 50 年代編寫的跳棋遊戲程序。

The amazing thing about this program was that Arthur Samuel himself wasn't a very good checkers player.

這個項目的神奇之處在於，亞瑟-塞繆爾本人並不是一個很好的跳棋手。

What he did was he had programmed a computer to play maybe tens of thousands of games against itself.

他所做的就是給計算機編程，讓它自己跟自己玩幾萬場遊戲。

By watching what sorts of board positions tend to lead to wins, and what positions tend to lead to losses, the checkers playing program learned over time what are good or bad board positions.

通過觀察什麼樣的棋盤位置容易贏棋，什麼樣的棋盤位置容易輸棋，跳棋遊戲程序逐漸學會了什麼是好棋盤位置，什麼是壞棋盤位置。

By trying to get to good and avoid bad positions, this program learned to get better and better at playing checkers.

通過努力進入好的位置和避免壞的位置，這個程序學會了在下跳棋時越來越好。

Because the computer had the patience to play tens of thousands of games against itself, it was able to get so much checkers playing experience that eventually it became a better checkers player than Arthur Samuel himself.

由於計算機有耐心與自己對弈數萬局，是以它獲得了大量的跳棋經驗，最終成為比亞瑟-塞繆爾本人更出色的跳棋選手。

Now, throughout these videos, besides me trying to talk about stuff, I'll occasionally ask you a question to help make sure you understand the content.

現在，在這些視頻中，除了我努力講述內容外，我還會偶爾問你一個問題，以幫助確保你理解內容。

Here's one about what happens if the computer had played far fewer games.

這裡有一個關於如果電腦玩的遊戲少得多會發生什麼情況的例子。

Please take a look and pick whichever you think is a better answer.

請看一看，並選出您認為較好的答案。

Thanks for looking at the quiz.

感謝您觀看測驗。

So if you had selected this answer, would have made it worse, then you got it right.

所以，如果你選擇了這個答案，會使情況變得更糟，那麼你就答對了。

In general, the more opportunities you give a learning algorithm to learn, the better it will perform.

一般來說，給學習算法的學習機會越多，它的表現就越好。

If you didn't select the correct answer the first time, that's totally okay too.

如果您第一次沒有選擇正確答案，也完全沒關係。

The point of these quiz questions isn't to see if you can get them all correct on the first try.

這些問答題的重點並不是看您是否能在第一次嘗試時全部答對。

These questions are here just to help you practice the concepts you're learning.

這些問題只是為了幫助您練習所學的概念。

Arthur Samuel's definition was a rather informal one, but in the next two videos, we'll dive deeper together into what are the major types of machine learning algorithms.

亞瑟-塞繆爾的定義比較隨意，但在接下來的兩段視頻中，我們將一起深入探討機器學習算法的主要類型。

In this class, you learn about many different learning algorithms.

在這門課中，你將學習到許多不同的學習算法。

The two main types of machine learning are supervised learning and unsupervised learning.

機器學習的兩種主要類型是監督學習和無監督學習。

We'll define what these terms mean more in the next couple of videos.

我們將在接下來的幾個視頻中進一步解釋這些術語的含義。

Of these two, supervised learning is the type of machine learning that is used most in many real-world applications and that has seen the most rapid advancement and innovation.

在這兩種機器學習中，監督學習是在許多實際應用中使用最多的機器學習類型，其進步和創新也最為迅速。

In this specialization, which has three causes in total, the first and second causes will focus on supervised learning, and the third will focus on unsupervised learning, recommender systems, and reinforcement learning.

本專業共有三個方向，第一和第二方向側重於監督學習，第三方向側重於無監督學習、推薦系統和強化學習。

By far, the most used types of learning algorithms today are supervised learning, unsupervised learning, and recommender systems.

到目前為止，使用最多的學習算法類型是監督學習、無監督學習和推薦系統。

The other thing we're going to spend a lot of time on in this specialization is practical advice for applying learning algorithms.

在本專業中，我們還將花大量時間討論應用學習算法的實用建議。

This is something I feel pretty strongly about.

這一點我深有感觸。

Teaching about learning algorithms is like giving someone a set of tools.

教授學習算法就像給別人一套工具。

Equally important or even more important than making sure you have great tools is making sure you know how to apply them.

與確保擁有好工具同樣重要甚至更重要的是，確保知道如何應用這些工具。

Because what good is it if someone were to give you a state-of-the-art hammer or a state-of-the-art hand drill and say, good luck, now you have all the tools you need to build a three-story house.

因為如果有人給你一把最先進的錘子或一把最先進的手電鑽，然後說，祝你好運，現在你擁有了建造三層樓房子所需的所有工具，那又有什麼用呢？

Doesn't really work like that.

其實不是這樣的。

So too in machine learning, making sure you have the tools is really important, and so it's making sure that you know how to apply the tools of machine learning effectively.

是以，在機器學習中，確保你擁有工具真的很重要，所以要確保你知道如何有效地應用機器學習工具。

That's what you get in this class, the tools as well as the skills of applying them effectively.

這就是你在這門課上所獲得的，工具以及有效應用這些工具的技能。

I regularly visit with friends and teams in some of the top tech companies, and even today, I see experienced machine learning teams apply machine learning algorithms to some problems, and sometimes they've been going at it for six months without much success.

我經常拜訪一些頂級科技公司的朋友和團隊，即使在今天，我也能看到經驗豐富的機器學習團隊將機器學習算法應用到一些問題上，有時他們已經堅持了六個月，卻沒有取得什麼成效。

When I look at what they're doing, I sometimes feel like I could have told them six months ago that the current approach won't work and there's a different way of using these tools that will give them a much better chance of success.

當我看到他們正在做的事情時，我有時會覺得，我本可以在六個月前告訴他們，目前的方法行不通，有一種使用這些工具的不同方法，會給他們帶來更大的成功機會。

So in this class, one of the relatively unique things you learn is, you learn a lot about the best practices for how to actually develop a practical, valuable machine learning system.

是以，在這門課上，你能學到的相對獨特的東西之一就是，你能學到很多關於如何實際開發一個實用、有價值的機器學習系統的最佳實踐。

This way, you're less likely to end up in one of those teams that end up losing six months going in the wrong direction.

這樣，你就不太可能成為那些在錯誤的方向上失敗了六個月的團隊中的一員。

In this class, you gain a sense of how the most skilled machine learning engineers build systems, and I hope you finish this class as one of those very rare people in today's world that know how to design and build serious machine learning systems.

在這門課上，你將瞭解到最熟練的機器學習工程師是如何構建系統的，我希望你在學完這門課後，能成為當今世界上少有的知道如何設計和構建嚴肅的機器學習系統的人。

So that's machine learning.

這就是機器學習。

In the next video, let's look more deeply at what is supervised learning, and also what is unsupervised learning.

在下一個視頻中，讓我們更深入地瞭解什麼是有監督學習，什麼是無監督學習。

In addition, you learn when you might want to use each of them, supervised and unsupervised learning.

此外，您還將學習何時需要使用監督學習和無監督學習。

I'll see you in the next video.

我們下期視頻再見。