更改

机器学习，在重组为一个独立的领域之后，与20世纪90年代开始蓬勃发展。该领域的目标从实现人工智能转变为解决实际中的可解决问题。它将焦点从它从人工智能继承的符号方法转移到从统计学和概率论中借鉴的方法和模型。截止至2019年，许多资料都继续断言机器学习仍然是人工智能的一个子领域。然而，一些该领域的从业者（例如丹尼尔 · 休姆 Daniel Hulme博士，他既教授人工智能，又经营着一家在该领域运营的公司），则认为机器学习和人工智能是分开的。

机器学习，在重组为一个独立的领域之后，与20世纪90年代开始蓬勃发展。该领域的目标从实现人工智能转变为解决实际中的可解决问题。它将焦点从它从人工智能继承的符号方法转移到从统计学和概率论中借鉴的方法和模型。截止至2019年，许多资料都继续断言机器学习仍然是人工智能的一个子领域。然而，一些该领域的从业者（例如丹尼尔 · 休姆 Daniel Hulme博士，他既教授人工智能，又经营着一家在该领域运营的公司），则认为机器学习和人工智能是分开的。

   --~~~到这

    

Ref name"elements"

Ref name"elements"

Machine learning also has intimate ties to optimization: many learning problems are formulated as minimization of some loss function on a training set of examples. Loss functions express the discrepancy between the predictions of the model being trained and the actual problem instances (for example, in classification, one wants to assign a label to instances, and models are trained to correctly predict the pre-assigned labels of a set of examples). The difference between the two fields arises from the goal of generalization: while optimization algorithms can minimize the loss on a training set, machine learning is concerned with minimizing the loss on unseen samples.

Machine learning also has intimate ties to optimization: many learning problems are formulated as minimization of some loss function on a training set of examples. Loss functions express the discrepancy between the predictions of the model being trained and the actual problem instances (for example, in classification, one wants to assign a label to instances, and models are trained to correctly predict the pre-assigned labels of a set of examples). The difference between the two fields arises from the goal of generalization: while optimization algorithms can minimize the loss on a training set, machine learning is concerned with minimizing the loss on unseen samples.

机器学习与优化也有着密切的联系: 许多学习问题被表述为最小化训练样本集上的某些'''损失函数 Loss function'''。损失函数表示正在训练的模型预测结果与实际数据之间的差异（例如，在分类问题中，人们的目标是给一个未知的实例分配其对应标签，而模型经过训练学习到的是如何正确地为一组实例标记事先已知的标签）。这两个领域之间的差异源于泛化的目标: 优化算法可以最小化训练集上的损失，而机器学习关注于最小化未知样本上的损失。

机器学习与优化也有着密切的联系: 许多学习问题被表述为最小化训练样本集上的某些'''损失函数 Loss Function'''。损失函数表示正在训练的模型预测结果与实际数据之间的差异（例如，在分类问题中，人们的目标是给一个未知的实例分配其对应标签，而模型经过训练学习到的是如何正确地为一组实例标记事先已知的标签）。这两个领域之间的差异源于泛化的目标: 优化算法可以最小化训练集上的损失，而机器学习关注于最小化未知样本上的损失。

=== 与统计学的关系 Relation to statistics ===

=== 与统计学的关系 Relation to statistics ===

机器学习算法及其性能的计算分析是'''理论计算机科学 Theoretical computer science'''的一个分支，也被称为'''机器学习理论 Computational learning theory'''。由于训练集是有限的，未来是不确定的，学习理论通常不能保证算法的性能。相反，性能的概率界限是相当常见的。'''偏差-方差分解 Bias–variance decomposition'''就是量化泛化'''误差 Errors and residuals'''的一种方法。

机器学习算法及其性能的计算分析是'''理论计算机科学 Theoretical computer science'''的一个分支，也被称为'''机器学习理论 Computational learning theory'''。由于训练集是有限的，未来是不确定的，学习理论通常不能保证算法的性能。相反，性能的概率界限是相当常见的。'''偏差-方差分解 Bias–variance decomposition'''就是量化泛化'''误差 Errors and residuals'''的一种方法。

Similarity learning is an area of supervised machine learning closely related to regression and classification, but the goal is to learn from examples using a similarity function that measures how similar or related two objects are. It has applications in ranking, recommendation systems, visual identity tracking, face verification, and speaker verification.

Similarity learning is an area of supervised machine learning closely related to regression and classification, but the goal is to learn from examples using a similarity function that measures how similar or related two objects are. It has applications in ranking, recommendation systems, visual identity tracking, face verification, and speaker verification.

'''相似性学习 Similarity learning'''是监督学习领域中与回归和分类密切相关的一个领域，但其目标是从实例中学习如何通过使用相似性函数来衡量两个对象之间的相似程度。它在排名、推荐系统、视觉身份跟踪、人脸验证和语者验证 Speaker verification等方面都有应用。

'''相似性学习 Similarity learning'''是监督学习领域中与回归和分类密切相关的一个领域，但其目标是从实例中学习如何通过使用相似性函数来衡量两个对象之间的相似程度。它在排名、推荐系统、视觉身份跟踪、人脸验证和'''语者验证 Speaker verification'''等方面都有应用。

{} / ref

{} / ref

特征学习可以是有监督的，也可以是无监督的。在有监督的特征学习中，可以利用标记输入数据学习特征。例如'''人工神经网络 Artificial neural networks，ANN'''、'''多层感知机 Multilayer perceptrons，MLP'''和受控字典式学习模型 Supervised dictionary learning model，SDLM。在无监督的特征学习中，特征是通过未标记的输入数据进行学习的。例如，'''字典学习 Dictionary learning'''、'''独立元素分析 Independent component analysis'''、'''自动编码器 Autoencoders'''、'''矩阵分解 Matrix factorization'''和各种形式的聚类

特征学习可以是有监督的，也可以是无监督的。在有监督的特征学习中，可以利用标记输入数据学习特征。例如'''人工神经网络 Artificial neural networks，ANN'''、'''多层感知机 Multilayer perceptrons，MLP'''和受控字典式学习模型 Supervised dictionary learning model，SDLM。在无监督的特征学习中，特征是通过未标记的输入数据进行学习的。例如，'''字典学习 Dictionary learning'''、'''独立元素分析 Independent component analysis'''、'''自动编码器 Autoencoders'''、'''矩阵分解 Matrix factorization'''和各种形式的聚类。

Sparse dictionary learning is a feature learning method where a training example is represented as a linear combination of basis functions, and is assumed to be a sparse matrix. The method is strongly NP-hard and difficult to solve approximately. A popular heuristic method for sparse dictionary learning is the K-SVD algorithm. Sparse dictionary learning has been applied in several contexts. In classification, the problem is to determine the class to which a previously unseen training example belongs. For a dictionary where each class has already been built, a new training example is associated with the class that is best sparsely represented by the corresponding dictionary. Sparse dictionary learning has also been applied in image de-noising. The key idea is that a clean image patch can be sparsely represented by an image dictionary, but the noise cannot.

Sparse dictionary learning is a feature learning method where a training example is represented as a linear combination of basis functions, and is assumed to be a sparse matrix. The method is strongly NP-hard and difficult to solve approximately. A popular heuristic method for sparse dictionary learning is the K-SVD algorithm. Sparse dictionary learning has been applied in several contexts. In classification, the problem is to determine the class to which a previously unseen training example belongs. For a dictionary where each class has already been built, a new training example is associated with the class that is best sparsely represented by the corresponding dictionary. Sparse dictionary learning has also been applied in image de-noising. The key idea is that a clean image patch can be sparsely represented by an image dictionary, but the noise cannot.

稀疏词典学习是一种特征学习方法，在这种方法中，一个训练样本被表示为基函数的线性组合，并假设为稀疏矩阵。该方法具有强 NP- 困难性并且近似求解困难。一种流行的'''启发式 Heuristic'''稀疏字典学习方法是 K-SVD 算法。稀疏词典学习已经应用于以下几种情况下：在分类中，问题在于如何确定先前未见的训练样本所属的类；对于已经构建了每个类的字典，一个新的训练示例将与相应的字典最好地稀疏表示的类相关联。稀疏字典学习也被广泛应用到图像去噪的问题中。其关键思想是，一个干净的图像'''补丁 patch'''可以由图像字典稀疏地表示，但噪声不能。

稀疏词典学习是一种特征学习方法，在这种方法中，一个训练样本被表示为基函数的线性组合，并假设为稀疏矩阵。该方法具有强 NP- Hard性并且近似求解困难。一种流行的'''启发式 Heuristic'''稀疏字典学习方法是 K-SVD 算法。稀疏词典学习已经应用于以下几种情况下：在分类中，问题在于如何确定先前未见的训练样本所属的类；对于已经构建了每个类的字典，一个新的训练示例将与相应的字典最好地稀疏表示的类相关联。稀疏字典学习也被广泛应用到图像去噪的问题中。其关键思想是，一个干净的图像'''补丁 patch'''可以由图像字典稀疏地表示，但噪声不能。

==== 异常检测 Anomaly detection ====

==== 异常检测 Anomaly detection ====

Machine learning approaches in particular can suffer from different data biases. A machine learning system trained on current customers only may not be able to predict the needs of new customer groups that are not represented in the training data. When trained on man-made data, machine learning is likely to pick up the same constitutional and unconscious biases already present in society. Language models learned from data have been shown to contain human-like biases. Machine learning systems used for criminal risk assessment have been found to be biased against black people. In 2015, Google photos would often tag black people as gorillas, and in 2018 this still was not well resolved, but Google reportedly was still using the workaround to remove all gorillas from the training data, and thus was not able to recognize real gorillas at all. Similar issues with recognizing non-white people have been found in many other systems. In 2016, Microsoft tested a chatbot that learned from Twitter, and it quickly picked up racist and sexist language. Because of such challenges, the effective use of machine learning may take longer to be adopted in other domains. Concern for fairness in machine learning, that is, reducing bias in machine learning and propelling its use for human good is increasingly expressed by artificial intelligence scientists, including Fei-Fei Li, who reminds engineers that "There’s nothing artificial about AI...It’s inspired by people, it’s created by people, and—most importantly—it impacts people. It is a powerful tool we are only just beginning to understand, and that is a profound responsibility.”

Machine learning approaches in particular can suffer from different data biases. A machine learning system trained on current customers only may not be able to predict the needs of new customer groups that are not represented in the training data. When trained on man-made data, machine learning is likely to pick up the same constitutional and unconscious biases already present in society. Language models learned from data have been shown to contain human-like biases. Machine learning systems used for criminal risk assessment have been found to be biased against black people. In 2015, Google photos would often tag black people as gorillas, and in 2018 this still was not well resolved, but Google reportedly was still using the workaround to remove all gorillas from the training data, and thus was not able to recognize real gorillas at all. Similar issues with recognizing non-white people have been found in many other systems. In 2016, Microsoft tested a chatbot that learned from Twitter, and it quickly picked up racist and sexist language. Because of such challenges, the effective use of machine learning may take longer to be adopted in other domains. Concern for fairness in machine learning, that is, reducing bias in machine learning and propelling its use for human good is increasingly expressed by artificial intelligence scientists, including Fei-Fei Li, who reminds engineers that "There’s nothing artificial about AI...It’s inspired by people, it’s created by people, and—most importantly—it impacts people. It is a powerful tool we are only just beginning to understand, and that is a profound responsibility.”

特别是机器学习方法可能会受到不同数据偏差的影响。仅针对当前客户的机器学习系统可能无法预测培训数据中没有表示的新客户群体的需求。当机器学习接受人造数据的训练时，很可能会挑选出社会中已经存在的同样的宪法和无意识的偏见。从数据中学到的语言模型已经被证明包含了类似人类的偏见。用于犯罪风险评估的机器学习系统被发现对黑人有偏见。在2015年，谷歌照片经常把黑人标记为大猩猩，而在2018年，这个问题仍然没有得到很好的解决，但据报道，谷歌仍然在使用变通方法从训练数据中删除所有大猩猩，因此根本无法识别真正的大猩猩。在许多其他系统中也发现了识别非白人的类似问题。2016年，微软测试了一个从 Twitter 上学来的聊天机器人，它很快就学会了种族主义和性别歧视的语言。由于这些挑战，机器学习的有效应用可能需要更长的时间才能在其他领域内广泛应用。人工智能科学家越来越关注机器学习中的公平问题，即减少机器学习中的偏见，推动机器学习为人类的利益服务。李等人提醒工程师们：“人工智能没有任何人为的东西... ... 它受到人的启发，由人创造，最重要的是，它会影响人。”，”这是一个强大的工具，我们才刚刚开始理解，这是一项意义深远的责任。”

从数据中学到的语言模型已经被证明包含了类似人类的偏见。用于犯罪风险评估的机器学习系统被发现对黑人有偏见。在2015年，谷歌照片经常把黑人标记为大猩猩，而在2018年，这个问题仍然没有得到很好的解决，但据报道，谷歌仍然在使用变通方法从训练数据中删除所有大猩猩，因此根本无法识别真正的大猩猩。在许多其他系统中也发现了识别非白人的类似问题。2016年，微软测试了一个从 Twitter 上学来的聊天机器人，它很快就学会了种族主义和性别歧视的语言。由于这些挑战，机器学习的有效应用可能需要更长的时间才能在其他领域内广泛应用。人工智能科学家越来越关注机器学习中的公平问题，即减少机器学习中的偏见，推动机器学习为人类的利益服务。李等人提醒工程师们：“人工智能没有任何人为的东西... ... 它受到人的启发，由人创造，最重要的是，它会影响人。”，”这是一个强大的工具，我们才刚刚开始理解，这是一项意义深远的责任。”

== 模型评估 Model assessments ==

== 模型评估 Model assessments ==