Let's give a slightly more formal definition of unsupervised learning and take a quick look at some other types of unsupervised learning other than clustering.

讓我們給無監督學習下一個稍微正式一點的定義，並快速瞭解一下聚類以外的其他幾種無監督學習類型。

Whereas in supervised learning, the data comes with both inputs x and output labels y, in unsupervised learning, the data comes only with inputs x but not output labels y, and the algorithm has to find some structure or some pattern or something interesting in the data.

在有監督學習中，數據既有輸入 x 又有輸出標籤 y，而在無監督學習中，數據只有輸入 x 而沒有輸出標籤 y，算法必須在數據中找到一些結構、模式或有趣的東西。

We've seen just one example of unsupervised learning called a clustering algorithm, which groups similar data points together.

我們只看到了一個無監督學習的例子，叫做聚類算法，它將相似的數據點歸類在一起。

In this specialization, you learn about clustering as well as two other types of unsupervised learning.

在本專業中，您將學習聚類以及其他兩種無監督學習。

One is called anomaly detection, which is used to detect unusual events.

其中一種稱為異常檢測，用於檢測異常事件。

This turns out to be really important for fraud detection in the financial system, where unusual events, unusual transactions could be a sign of fraud and for many other applications.

在金融系統中，異常事件、異常交易都可能是欺詐的跡象。

You also learn about dimensionality reduction.

您還可以學習降維。

This lets you take a big dataset and almost magically compress it to a much smaller dataset while losing as little information as possible.

這可以讓你獲取一個大數據集，並幾乎神奇地將其壓縮到更小的數據集，同時儘可能減少資訊丟失。

In case anomaly detection and dimensionality reduction don't seem to make too much sense to you yet, don't worry about it.

如果你對異常檢測和降維還不太瞭解，也不用擔心。

We'll get to this later in this specialization.

我們將在後面的專業課程中討論這個問題。

Now, I'd like to ask you another question to help you check your understanding.

現在，我想再問你一個問題，以幫助你檢查自己的理解。

No pressure, if you don't get it right on the first try, it's totally fine.

不要有壓力，如果第一次沒做對，也沒關係。

Please select any of the following that you think are examples of unsupervised learning.

請選擇下列你認為屬於無監督學習的例子。

Two are unsupervised examples and two are supervised learning examples.

兩個是無監督示例，兩個是有監督學習示例。

Please take a look.

請看一看。

Maybe you remember the spam filtering problem.

也許你還記得垃圾郵件過濾問題。

If you have labeled data, labeled as spam or non-spam e-mail, you can treat this as a supervised learning problem.

如果您有標註數據，標註為垃圾郵件或非垃圾郵件，您就可以將其視為監督學習問題。

The second example, the news story example, that's exactly the Google News and Tandem example that you saw in the last video.

第二個例子，新聞故事的例子，正是你在上一個視頻中看到的 Google News 和 Tandem 的例子。

You can approach that using a clustering algorithm to group news articles together.

您可以使用聚類算法將新聞文章分組。

That would use unsupervised learning.

這將使用無監督學習。

The market segmentation example that I talked about a little bit earlier, you can do that as an unsupervised learning problem as well, because you can give your algorithm some data and ask it to discover market segments automatically.

我剛才談到的市場細分例子，也可以作為無監督學習問題來解決，因為你可以給算法一些數據，讓它自動發現市場細分。

The final example on diagnosing diabetes.

最後一個例子是診斷糖尿病。

Well, actually, that's a lot like our breast cancer example from the supervised learning videos.

其實，這很像監督學習視頻中的乳腺癌例子。

Only instead of benign or malignant tumors, we instead have diabetes or not diabetes.

只不過，我們得的不是良性或惡性腫瘤，而是糖尿病或非糖尿病。

You can approach this as a supervised learning problem, just like we did for the breast tumor classification problem.

你可以把它當作一個有監督的學習問題來處理，就像我們處理乳腺腫瘤分類問題一樣。

Even though in this and the last video, we've talked mainly about clustering, in later videos in this specialization, we'll dive much more deeply into anomaly detection and dimensionality reduction as well.

儘管在本視頻和上一個視頻中，我們主要討論了聚類，但在本專業的後續視頻中，我們還將更深入地討論異常檢測和降維。

That's unsupervised learning.

這就是無監督學習。

Before we wrap up this section, I want to share with you something that I find really exciting and useful, which is the use of Jupyter Notebooks in machine learning.

在結束本節內容之前，我想和大家分享一些我覺得非常令人興奮和有用的東西，那就是 Jupyter Notebooks 在機器學習中的應用。

Let's take a look at that in the next video.

讓我們在下一個視頻中看看。