463
个编辑
更改
无编辑摘要
Machine learning (ML) is the study of computer algorithms that improve automatically through experience. It is seen as a subset of artificial intelligence. Machine learning algorithms build a mathematical model based on sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to do so.}} Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision, where it is difficult or infeasible to develop conventional algorithms to perform the needed tasks.
Machine learning (ML) is the study of computer algorithms that improve automatically through experience. It is seen as a subset of artificial intelligence. Machine learning algorithms build a mathematical model based on sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to do so.}} Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision, where it is difficult or infeasible to develop conventional algorithms to perform the needed tasks.
机器学习(ML)是研究通过经验自动改进的计算机算法。它被看作是人工智能的一个子集。机器学习算法建立一个基于样本数据的数学模型，称为“训练数据” ，以便在没有明确编程的情况下进行预测或决策。}机器学习算法被广泛应用于各种各样的应用中，如电子邮件过滤和计算机视觉，在这些应用中，开发传统的算法来执行所需的任务是困难的或不可行的。
'''机器学习 ML'''关于如何通过经验学习来实现自动改进的计算机算法研究。它被看作是人工智能的一个子集''（属于人工智能的范畴）''。机器学习算法的基础是建立一个基于样本数据（称为“训练数据”）的数学模型，以便在没有明确编程策略的情况下进行预测或决策。机器学习算法被广泛应用于各种各样的场景中，如电子邮件过滤和计算机视觉等。而这些问题，如果仅仅使用传统算法来实现是十分困难的，甚至是或不可行的。
Machine learning is closely related to computational statistics, which focuses on making predictions using computers. The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning. Data mining is a related field of study, focusing on exploratory data analysis through unsupervised learning.{{refn|Machine learning and pattern recognition "can be viewed as two facets of the same field." In its application across business problems, machine learning is also referred to as predictive analytics.
Machine learning is closely related to computational statistics, which focuses on making predictions using computers. The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning. Data mining is a related field of study, focusing on exploratory data analysis through unsupervised learning.{{refn|Machine learning and pattern recognition "can be viewed as two facets of the same field." In its application across business problems, machine learning is also referred to as predictive analytics.
机器学习与计算机数据学习密切相关，但后者更加专注于利用计算机进行预测。数学优化问题的研究为机器学习领域提供了方法、理论和应用领域。数据挖掘也是一个与机器学习相关的研究领域，侧重于通过无监督学习进行探索性的数据分析。{{ refn | 机器学习和模式识别“可以看作是同一领域的两个方面”。在应用于商业问题时，机器学习也被称为预测分析学习。
== Overview ==
== 概述 Overview ==
Machine learning involves computers discovering how they can perform tasks without being explicitly programmed to do so. For simple tasks assigned to computers, it is possible to program algorithms telling the machine how to execute all steps required to solve the problem at hand; on the computer's part, no learning is needed. For more advanced tasks, it can be challenging for a human to manually create the needed algorithms. In practice, it can turn out to be more effective to help the machine develop its own algorithm, rather than have human programmers specify every needed step.<ref name = "Alpaydin2020">{{cite book
Machine learning involves computers discovering how they can perform tasks without being explicitly programmed to do so. For simple tasks assigned to computers, it is possible to program algorithms telling the machine how to execute all steps required to solve the problem at hand; on the computer's part, no learning is needed. For more advanced tasks, it can be challenging for a human to manually create the needed algorithms. In practice, it can turn out to be more effective to help the machine develop its own algorithm, rather than have human programmers specify every needed step.<ref name = "Alpaydin2020">{{cite book
Machine learning involves computers discovering how they can perform tasks without being explicitly programmed to do so. For simple tasks assigned to computers, it is possible to program algorithms telling the machine how to execute all steps required to solve the problem at hand; on the computer's part, no learning is needed. For more advanced tasks, it can be challenging for a human to manually create the needed algorithms. In practice, it can turn out to be more effective to help the machine develop its own algorithm, rather than have human programmers specify every needed step.<ref name = "Alpaydin2020">{{cite book
Machine learning involves computers discovering how they can perform tasks without being explicitly programmed to do so. For simple tasks assigned to computers, it is possible to program algorithms telling the machine how to execute all steps required to solve the problem at hand; on the computer's part, no learning is needed. For more advanced tasks, it can be challenging for a human to manually create the needed algorithms. In practice, it can turn out to be more effective to help the machine develop its own algorithm, rather than have human programmers specify every needed step.<ref name = "Alpaydin2020">{{cite book
机器学习问题涉及到计算机如何实现在没有明确编程策略的情况下完成任务。而对于分配给计算机的简单任务，可以编写算法程序，告诉机器如何执行解决手头问题所需的所有步骤，这种方法对于计算机来说，是不需要“学习”的。而对于更高级的任务，手动创建解决问题的算法对人们目前的编程水平来说是十分困难的。实际上，帮助机器学习、开发自己的算法比让程序员人工指定解决问题的每个步骤更有效率。 2020"{ cite book"
| author = Ethem Alpaydin
| author = Ethem Alpaydin
The discipline of machine learning employs various approaches to help computers learn to accomplish tasks where no fully satisfactory algorithm is available. In cases where vast numbers of potential answers exist, one approach is to label some of the correct answers as valid. This can then be used as training data for the computer to improve the algorithm(s) it uses to determine correct answers. For example, to train a system for the task of digital character recognition, the MNIST dataset has often been used.
The discipline of machine learning employs various approaches to help computers learn to accomplish tasks where no fully satisfactory algorithm is available. In cases where vast numbers of potential answers exist, one approach is to label some of the correct answers as valid. This can then be used as training data for the computer to improve the algorithm(s) it uses to determine correct answers. For example, to train a system for the task of digital character recognition, the MNIST dataset has often been used.
机器学习的目标是使用各种方法来帮助计算机学习待完成的目标任务，而这些任务并没有公认、明确的解决算法可用。在存在大量潜在答案的情况下，一种解决方法是将一些正确答案样本标记为有效并作为计算机的训练数据，来改进给出正确答案对应的机器学习算法。例如，为了训练一个模型来完成数字字符识别的任务，科学家们常常使用 MNIST 这一带标签的数据集。
=== Machine learning approaches ===
=== 机器学习方法 Machine learning approaches ===
{{Anchor|Algorithm types}}
{{Anchor|Algorithm types}}
Early classifications for machine learning approaches sometimes divided them into three broad categories, depending on the nature of the "signal" or "feedback" available to the learning system. These were:
Early classifications for machine learning approaches sometimes divided them into three broad categories, depending on the nature of the "signal" or "feedback" available to the learning system. These were:
机器学习的方法在早期根据学习系统可用的“信号”或“反馈”的性质被分为三大类，它们是:
<br/>[[Supervised learning]]: The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that [[Map (mathematics)|maps]] inputs to outputs.
<br/>[[Supervised learning]]: The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that [[Map (mathematics)|maps]] inputs to outputs.
<br/>Supervised learning: The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that maps inputs to outputs.
<br/>Supervised learning: The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that maps inputs to outputs.
Br / 监督式学习: 计算机由一个“老师”给出一个输入和他们想要的输出的例子，目的是学习一个将输入映射到输出的一般规则。
Br / '''监督学习 Supervised learning''': 计算机由一个“老师”给出一个输入和他们想要的输出的例子，其目的是学习一个将输入映射到输出的一般规则。
<br/>[[Unsupervised learning]]: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end ([[feature learning]]).
<br/>[[Unsupervised learning]]: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end ([[feature learning]]).
<br/>Unsupervised learning: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end (feature learning).
<br/>Unsupervised learning: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end (feature learning).
Br / 非监督式学习: 没有给学习算法贴标签，让它自己在输入中寻找结构。非监督式学习本身可以是一个目标(在数据中发现隐藏的模式) ，也可以是一个达到目标的手段(特性学习)。
Br / '''无监督学习 Unsupervised learning''': 没有给学习算法贴标签，让程序自己在输入中发现潜在规则。非监督式学习本身可以是一个目标（如在数据中发现隐藏的模式），也可以是一个达到目标的手段（如'''特性学习 Feature learning'''）。
<br/>[[Reinforcement learning]]: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as [[Autonomous car|driving a vehicle]] or playing a game against an opponent) As it navigates its problem space, the program is provided feedback that's analogous to rewards, which it tries to maximise. <ref name="bishop2006"/>
<br/>[[Reinforcement learning]]: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as [[Autonomous car|driving a vehicle]] or playing a game against an opponent) As it navigates its problem space, the program is provided feedback that's analogous to rewards, which it tries to maximise. <ref name="bishop2006"/>
<br/>Reinforcement learning: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as driving a vehicle or playing a game against an opponent) As it navigates its problem space, the program is provided feedback that's analogous to rewards, which it tries to maximise.
<br/>Reinforcement learning: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as driving a vehicle or playing a game against an opponent) As it navigates its problem space, the program is provided feedback that's analogous to rewards, which it tries to maximise.
Br / 强化学习: 一个计算机程序与一个动态环境相互作用，在这个环境中它必须执行一个特定的目标(比如驾驶一辆车或者与对手玩一个游戏)当它导航它的问题空间时，程序被提供类似于奖励的反馈，它试图将奖励最大化。
Br / '''强化学习 Reinforcement learning''': 计算机程序与某动态环境相互作用，同时在这个环境中它必须执行一个特定的目标（比如驾驶一辆车或者与对手玩一个游戏）。当它定位到它正确的问题空间时，程序会被提供类似于奖励的反馈，而算法的目标就是将奖励最大化。
Other approaches or processes have since developed that don't fit neatly into this three-fold categorisation, and sometimes more than one is used by the same machine learning system. For example topic modeling, dimensionality reduction or meta learning. <ref>{{cite book
Other approaches or processes have since developed that don't fit neatly into this three-fold categorisation, and sometimes more than one is used by the same machine learning system. For example topic modeling, dimensionality reduction or meta learning. <ref>{{cite book
除了以上这三种方法，也存在其他的方法或流程，它们并不能完全符合这三种分类标准，有时候同一个机器学习系统也可能使用了不止一种方法。例如，'''话题建模 Topic modeling'''，'''降维学习 Dimensionality reduction'''或者'''元学习 Meta learning'''。文档{ cite book
| authors = Pavel Brazdil, Christophe Giraud Carrier, Carlos Soares, Ricardo Vilalta
| authors = Pavel Brazdil, Christophe Giraud Carrier, Carlos Soares, Ricardo Vilalta
}}</ref> As of 2020, deep learning has become the dominant approach for much ongoing work in the field of machine learning .
}}</ref> As of 2020, deep learning has become the dominant approach for much ongoing work in the field of machine learning .
截至2020年，深度学习已经成为机器学习领域许多正在进行的工作的热门方法。
== 历史以及和其他领域的关系History and relationships to other fields ==
== 历史以及和其他领域的关系 History and relationships to other fields ==
{{see also|Timeline of machine learning}}
{{see also|Timeline of machine learning}}