Name: #5 機器學習專業 [課程 1，第 1 周，第 2 課] (#5 Machine Learning Specialization [Course 1, Week 1, Lesson 2])
Uploaded: 2024-12-31T04:01:24.000Z
Duration: 7 min 17 s

So supervised learning algorithms learn to predict input-output or x-to-y mappings.

是以，監督學習算法學會了預測輸入-輸出或 X-Y 映射。

關係子句

And in the last video, you saw that regression algorithms, which is a type of supervised learning algorithm, learns to predict numbers out of infinitely many possible numbers.

在上一個視頻中，你看到了迴歸算法，它是一種監督學習算法，學會從無限多的可能數字中預測數字。

There's a second major type of supervised learning algorithm called a classification algorithm.

第二種主要的監督學習算法叫做分類算法。

Take breast cancer detection as an example of a classification problem.

Say you're building a machine learning system so that doctors can have a diagnostic tool to detect breast cancer.

假設你正在構建一個機器學習系統，以便為醫生提供檢測乳腺癌的診斷工具。

This is important because early detection could potentially save a patient's life.

這一點非常重要，因為早期發現有可能挽救患者的生命。

Using a patient's medical records, your machine learning system tries to figure out if a tumor, that is a lump, is malignant, meaning cancerous or dangerous, or if that tumor, that lump, is benign, meaning that it's just a lump that isn't cancerous and isn't that dangerous.

利用患者的醫療記錄，您的機器學習系統會嘗試找出腫瘤（即腫塊）是否是惡性的，也就是癌症或危險的，或者該腫瘤、腫塊是否是良性的，也就是它只是一個腫塊，沒有癌變，也沒有那麼危險。

Some of my friends have actually been working on this specific problem.

我的一些朋友實際上一直在研究這個具體問題。

So maybe your dataset has tumors of various sizes, and these tumors are labeled as either benign, which I will designate in this example with a zero, or malignant, which I'll designate in this example with a one.

是以，也許你的數據集中有不同大小的腫瘤，這些腫瘤被標記為良性（在本例中我將用 0 表示）或惡性（在本例中我將用 1 表示）。

You can then plot your data on a graph like this, where the horizontal axis represents the size of the tumor, and the vertical axis takes on only two values, zero or one, depending on whether the tumor is benign, zero, or malignant, one.

您可以將數據繪製成這樣的圖表：橫軸代表腫瘤的大小，縱軸只有兩個值，0 或 1，取決於腫瘤是良性的 0 還是惡性的 1。

One reason that this is different from regression is that we're trying to predict only a small number of possible outputs or categories.

這與迴歸不同的一個原因是，我們只試圖預測少量可能的輸出或類別。

In this case, two possible outputs, zero or one, benign or malignant.

在這種情況下，有兩種可能的輸出，0 或 1，良性或惡性。

This is different from regression, which tries to predict any number out of an infinitely many number of possible numbers.

這與迴歸不同，後者試圖從無限多的可能數字中預測任何數字。

So the fact that there are only two possible outputs is what makes this classification.

是以，只有兩種可能的輸出才是這種分類的原因。

Because there are only two possible outputs or two possible categories in this example, you can also plot this dataset on a line like this, where now I'm going to use two different symbols to denote the category, using a circle or an O to denote the benign examples, and a cross to denote the malignant examples.

因為在這個例子中只有兩種可能的輸出或兩種可能的類別，所以你也可以像這樣在一條線上繪製這個數據集，現在我要用兩種不同的符號來表示類別，用圓圈或 O 表示良性例子，用十字表示惡性例子。

If a new patient walks in for a diagnosis and they have a lump that is this size, then the question is, will your system classify this tumor as benign or malignant?

如果一位新患者前來就診，他們有一個這麼大的腫塊，那麼問題來了，你們的系統會將這個腫瘤歸類為良性還是惡性？

It turns out that in classification problems, you can also have more than two possible output categories.

事實證明，在分類問題中，也可能有兩個以上的輸出類別。

Maybe your learning algorithm can output multiple types of cancer diagnoses if it turns out to be malignant.

如果結果是惡性的，也許你的學習算法可以輸出多種癌症診斷結果。

So let's call two different types of cancer, type 1 and type 2.

是以，我們將兩種不同類型的癌症分別稱為 1 型和 2 型。

In this case, the algorithm would have three possible output categories it could predict.

在這種情況下，算法可以預測三種可能的輸出類別。

By the way, in classification, the terms output classes and output categories are often used interchangeably.

順便提一下，在分類中，輸出類和輸出類別這兩個術語經常交替使用。

So when I say class or category, when referring to the output, it means the same thing.

是以，當我說 "類 "或 "類別 "時，指的是輸出，意思是一樣的。

So to summarize, classification algorithms predict categories.

總而言之，分類算法可以預測類別。

Categories don't have to be numbers, it could be non-numeric.

類別不一定是數字，也可以是非數字。

For example, it can predict whether a picture is that of a cat or a dog, and it can predict if a tumor is benign or malignant.

例如，它可以預測一張圖片是貓還是狗，可以預測腫瘤是良性還是惡性。

Categories can also be numbers like 0 or 1 or 0 or 1 or 2.

類別也可以是數字，如 0 或 1 或 0 或 1 或 2。

But what makes classification different from regression when you're interpreting the numbers is that classification predicts a small, finite, limited set of possible output categories such as 0, 1, and 2, but not all possible numbers in between like 0.5 or 1.7.

但在解釋數字時，分類法與迴歸法的不同之處在於，分類法預測的是一小部分有限的可能輸出類別，如 0、1 和 2，而不是介於兩者之間的所有可能數字，如 0.5 或 1.7。

In the example of supervised learning that we've been looking at, we had only one input value, the size of the tumor.

在我們一直在研究的監督學習示例中，我們只有一個輸入值，即腫瘤的大小。

But you can also use more than one input value to predict an output.

但您也可以使用一個以上的輸入值來預測輸出。

Instead of just knowing the tumor size, say you also have each patient's age in years.

與其只知道腫瘤的大小，不如說你還知道每個病人的年齡（以歲為組織、部門）。

Your new dataset now has two inputs, age and tumor size.

您的新數據集現在有兩個輸入：年齡和腫瘤大小。

Plotting this new dataset, we're going to use circles to show patients whose tumors are benign, and crosses to show the patients with a tumor that was malignant.

在繪製這個新數據集時，我們將用圓圈表示腫瘤為良性的患者，用十字架表示腫瘤為惡性的患者。

So when a new patient comes in, the doctor can measure the patient's tumor size, and also record the patient's age.

是以，當有新病人來就診時，醫生可以測量病人的腫瘤大小，並記錄病人的年齡。

So given this, how can we predict if this patient's tumor is benign or malignant?

既然如此，我們該如何預測患者的腫瘤是良性還是惡性呢？

Well, given a dataset like this, what the learning algorithm might do is find some boundary that separates out the malignant tumors from the benign ones.

好吧，給定這樣一個數據集，學習算法可能要做的就是找到一些邊界，把惡性腫瘤和良性腫瘤區分開來。

So the learning algorithm has to decide how to fit a boundary line to this data.

是以，學習算法必須決定如何根據這些數據擬合一條邊界線。

The boundary line found by the learning algorithm would help the doctor with the diagnosis.

學習算法找到的邊界線將幫助醫生進行診斷。

In this case, the tumor is more likely to be benign.

在這種情況下，腫瘤更有可能是良性的。

From this example, we've seen how two inputs, the patient's age and tumor size, can be used.

從這個例子中，我們可以看到病人的年齡和腫瘤大小這兩個輸入是如何使用的。

In other machine learning problems, often many more input values are required.

在其他機器學習問題中，往往需要更多的輸入值。

My friends who worked on breast cancer detection use many additional inputs like the thickness of the tumor clump, uniformity of the cell size, uniformity of the cell shape, and so on.

我從事乳腺癌檢測的朋友使用了許多額外的輸入，如腫瘤團塊的厚度、細胞大小的均勻性、細胞形狀的均勻性等。

So to recap, supervised learning maps input X to output Y, where the learning algorithm learns from the quote, right answers.

是以，概括地說，監督式學習將輸入 X 映射到輸出 Y，學習算法從引用的正確答案中學習。

The two major types of supervised learning are regression and classification.

監督學習的兩大類型是迴歸和分類。

In a regression application, like predicting prices of houses, the learning algorithm has to predict numbers from infinitely many possible output numbers, whereas in classification, the learning algorithm has to make a prediction of a category out of a small set of possible outputs.

在迴歸應用中，比如預測房價，學習算法必須從無限多的可能輸出數字中預測數字，而在分類應用中，學習算法必須從一小部分可能的輸出中預測一個類別。

So you now know what is supervised learning, including both regression and classification.

現在你知道什麼是監督學習了吧，包括迴歸和分類。

Next, there's a second major type of machine learning called unsupervised learning.

其次，機器學習的第二大類型是無監督學習。

 Let's go on to the next video to see what that is.

讓我們繼續觀看下一個視頻，看看那是什麼。