[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["缺少我需要的資訊","missingTheInformationINeed","thumb-down"],["過於複雜/步驟過多","tooComplicatedTooManySteps","thumb-down"],["過時","outOfDate","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["示例/程式碼問題","samplesCodeIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間：2024-11-06 (世界標準時間)。"],[[["\u003cp\u003eMulti-class classification extends binary classification to handle more than two classes, often by breaking the problem down into multiple binary classifications.\u003c/p\u003e\n"],["\u003cp\u003eIn multi-class classification, each example is assigned to only one class, like classifying handwritten digits (0-9).\u003c/p\u003e\n"],["\u003cp\u003eIf an example can belong to multiple classes, it's called multi-label classification, which is a distinct but related concept.\u003c/p\u003e\n"],["\u003cp\u003eMulti-class classification can be achieved by creating a series of binary classifiers, each distinguishing between a subset of classes.\u003c/p\u003e\n"]]],[],null,["# Classification: Multi-class classification\n\nMulti-class classification can be treated as an extension of\n[**binary classification**](/machine-learning/glossary#binary_classification)\nto more than two classes. If each example can only be\nassigned to one class, then the classification problem can be handled as a\nbinary classification problem, where one class contains one of the multiple\nclasses, and the other class contains all the other classes put together.\nThe process can then be repeated for each of the original classes.\n\nFor example, in a three-class multi-class classification problem,\nwhere you're classifying examples with the labels **A** , **B** , and\n**C** , you could turn the problem into two separate binary classification\nproblems. First, you might create a binary classifier that categorizes examples\nusing the label **A+B** and the label **C** . Then, you could create a second\nbinary classifier that reclassifies the examples that are labeled **A+B**\nusing the label **A** and the label **B**.\n\nAn example of a multi-class problem is a handwriting classifier that takes\nan image of a handwritten digit and decides which digit, 0-9, is represented.\n\nIf class membership isn't exclusive, which is to say, an example can be\nassigned to multiple classes, this is known as a *multi-label* classification\nproblem.\n| Multi-class classification is explored more deeply in the [Multi-class neural networks](/machine-learning/crash-course/neural-networks/multi-class) section of the [Neural Networks](/machine-learning/crash-course/neural-networks) module.\n| **Key terms:**\n|\n- [Binary classification](/machine-learning/glossary#binary_classification) \n[Help Center](https://support.google.com/machinelearningeducation)"]]
