本文集翻译《Pattern Recognition and Machine Learning》这本经典机器学习图书的核心内容，本人也是初学者，也是第一次翻译，有兴趣就一起学习吧。

The problem of searching for patterns in data is a fundamental one . 

...

The field of pattern recognition is concerned with the automatic discovery of regularities in data through the use of computer algorithms and with the use of these regularities to take actions such as classifying the data into different categories. 

在数据集中找到一定的模式或规律是一个基础的问题。

。。。

模式识别领域与通过用计算机算法自动发现数据中的规律以及根据这些规律做出反应相关的，例如数据分类。

 

Consider the example of recognizing hand written digits,illustrated in Figure 1.1. Each digit corresponds to a 28×28 pixel image and so can be represented by a vector x comprising 784 real numbers. The goal is to build a machine that will take such a vector x as input and that will produce the identity of the digit 0,...,9 as the output.

考虑下面这个例子，识别手写数字。每一个数字都是一个28*28像素大小的图片，所以它们可以被表示成一个由784个实数组成的28*28的矩阵。这个例子的目标就是构建一个机器，它可以输入上面那个矩阵，然后产生一个0-9之间的一个数字。

...

Far better results can be obtained by adopting a machine learning approach in which a large set of N digits {x1,...,xN} called a training set is used to tune the parameters of an adaptive model. The categories of the digits in the training set are known in advance, typically by inspecting them individually and hand-labelling them. We can express the category of a digit using target vector t, which represents the identity of the corresponding digit.  Note that there is one such target vector t for each digit image x.

用一个合适的机器学习方法，可以得到更好的结果。在这个方法中，有一个由大量数字组成的数字集合，叫做训练集，被用于调整模型的参数。训练集中的数字的分类是事先知道的，一般是逐个进行识别或者手工标注他们。我们使用一个目标矩阵t 来表示这个分类。它能唯一代表一个对应的数字。注意：每一个数字图片x都有一个目标矩阵t与它对应。

The result of running the machine learning algorithm can be expressed as a function y(x) which takes a new digit image x as input and that generates an output vector y, encoded in the same way as the target vectors. The precise form of the function y(x) is determined during the training phase, also known as the learning phase, on the basis of the training data. Once the model is trained it can then determine the identity of new digit images, which are said to comprise a test set. The ability to categorize correctly new examples that differ from those used for training is known as generalization. In practical applications, the variability of the input vectors will be such that the training data can comprise only a tiny fraction of all possible input vectors, and so generalization is a central goal in pattern recognition.

机器学习运行的结果能够表示为一个函数y(x)，这个函数使用一个新的图片x作为输入，然后输出一个矩阵y，这个矩阵使用和目标矩阵一样的编码方式。决定这个函数y(x)精确形式的过程叫做训练阶段，也称为学习阶段。一旦模型训练完成它就可以识别一个新图片的正确的分类，这些新图片属于一个测试集。这种识别新图片的能力叫做泛化。在实际的应用程序中，训练集的数据仅是所有可能性的非常小的部分，所以泛化是模式识别的核心目的。

For most practical applications, the original input variables are typically preprocessed to transform them into some new space of variables where, it is hoped, the pattern recognition problem will be easier to solve.

在多数实际的应用程序中，原始的输入需要被预处理，这样做是希望能使这个模式识别问题更容易被解决。

For instance,in the digit recognition problem, the images of the digits are typically translated and scaled so that each digit is contained within a box of a fixed size. This greatly reduces the variability within each digit class, because the location and scale of all the digits are now the same, which makes it much easier for a subsequent pattern recognition algorithm to distinguish between the different classes. 

例如，在识别手写数字的问题中，这些数字图片都被重新裁剪，以便每张图片都为一个固定大小。这样可以极大的减少数字分类的可能性，因为所有数字的位置和大小都是相同的，使其更容易被接下来的模式识别算法区分。

This pre-processing stage is sometimes also called feature extraction. Note that new test data must be pre-processed using the same steps as the training data.

这个预处理的场景有时也叫做特征提取。注意，新的测试数据必须和训练数据一样被预处理。

Pre-processing might also be performed in order to speed up computation.

。。。

Care must be taken during pre-processing because often information is discarded, and if this information is important to the solution of the problem then the overall accuracy of the system can suffer.

预处理必须小心谨慎，因为信息经常会被删除，如果被删除的信息对于解决问题是非常重要的话，那么整个系统的精确性是非常糟糕的。

Applications in which the training data comprises examples of the input vectors along with their corresponding target vectors are known as supervised learning problems。

在应用程序中，如果训练数据的输入矩阵的样本都有对应的目标矩阵，那么这叫做有监督学习问题。

Cases such as the digit recognition example, in which the aim is to assign each input vector to one of a finite number of discrete categories, are called classification problems.

例如数字识别的例子，目标是将输入矩阵归为有限离散分类中的一个分类，加做归类问题。

 If the desired output consists of one or more continuous variables, then the task is called regression.

如果系统输出一个或者更多的连续变量，那么这个任务叫做回归。

In other pattern recognition problems, the training data consists of a set of input vectors x without any corresponding target values. The goal in such unsupervised learning problems may be to discover groups of similar examples within the data, where it is called clustering, or to determine the distribution of data within the input space, known as density estimation, or to project the data from a high-dimensional space down to two or three dimensions for the purpose of visualization.

还有 其他的模式识别问题，训练数据中的每个输入矩阵x没有任何相应的目标值。在这种无监督学习问题中，或许可以发现机组类型的样本，这叫做聚类；或者在输入空间内考察数据的分布，这叫做密度估计；或者将数据从高维空间降低到两维或者三维，为了可视化的目的。

Finally,the technique of reinforcement learning(SuttonandBarto,1998) is concerned with the problem of finding suitable actions to take in a given situation in order to maximize a reward.

最后，是强化学习技术，即在给定情况下找到并作出合适的反应，以使奖励最大化的问题。

。。。

A general feature of reinforcement learning is the trade-off between exploration, in which the system tries out new kinds of actions to see how effective they are, and exploitation, in which the system makes use of actions that are known to yield a high reward. Too strong a focus on either exploration or exploitation will yield poor results. Reinforcement learning continues to be an active area of machine learning research.

强化学习的一般特征是在探索中的交易，系统实验考察新行为的效果并利用之，系统就使用这些已知的可以获取高回报的行为。探索和利用需要保持平衡，无论哪一个太强都不会有好结果。强化学习一直是机器学习研究的活跃领域。