另外一些常见的学习类型不是被设计用于为输入创建分类，而是作出决定；它们统称决策问题。
The other common type of learning is designed not to create classifications of inputs, but to make decisions; these are called decision problems.
最后，您学习了如何处理表单数据，提供基于表单输入的服务器端验证。
Finally, you learned how to handle form data, providing server-side validation based on form input.
同样地，当你的大脑从真实世界的传感器上获取持续的输入时，大脑迅速学习将它映射到一种第六感中。
Similarly, when you're brain gets consistent input from a real-world sensor, it quickly learns to map that into a sort-of six sense.
如果通过算法作出的决定需要输入别的地方，这时分类学习是必要的。
Classification learning is often necessary when the decisions made by the algorithm will be required as input somewhere else.
作为可以快速且简单易读的脚本，在对外部进程的输入和输出进行文本处理方面，rexx无懈可击，而且学习和安装也不困难。
For quick and easily readable scripts that perform text manipulation on the inputs and outputs of external processes, Rexx is hard to beat, and not hard to learn or install.
所以，我们可以把-1看成一个常量输入，它的权系数theta在学习（或者用技术术语，称为培训）的过程中进行调整。
So, it is possible to treat -1 as a constant input whose weight, theta, is adjusted in learning, or, to use the technical term, training.
这些输入通常被称作“训练集”（原文为training set，译者注），它们是Agent尝试学习的样本。
These inputs, often called the "training set", are the examples from which the agent tries to learn.
Ubiquity可以处理自然语言形式的命令(译者注：当然是指英语)，因此理论上你可以凭直觉直接输入命令，而不用学习那些繁琐的语法。
Ubiquity handles natural language command phrases, so you can theoretically enter a command the way you intuit it, without having to learn the formal syntax.
为方便起见，您应该用less查看大文件，如在 less /etc/passwd 中那样（您可以通过输入man less学习更多关于 less 的知识）。
For convenience, should should view large files with less, as in less /etc/passwd (you can learn more about less by typing man less).
当您完成本文的学习后，您将会创建一个搜索页面，该页面能够接受用户的输入，并与数据库中的数据相比较，然后向用户返回查询的结果。
When you are finished with the tutorial, you will have a search page that can take input from users, compare it against the data in a database, and return results to the user.
和其他单手使用的键盘不同，二分之一键盘完全建立在QWERTY输入系统上，所以你不用再学习一种新的打字方法。
Unlike other one-hand keyboards, this one is based fully on the QWERTY system so you don't have to learn a new method of typing.
下个阶段是“无人工管理”的学习——完全没有人工指令的输入。
The next stage is "unsupervised" learning, in which instruction is entirely absent.
请注意这里提到的一个问题：在分类问题中，学习算法的目标是把给定输入中的错误最小化。
Notice something important here: in the classification problem, the goal of the learning algorithm is to minimize the error with respect to the given inputs.
这个步骤的目的是学习其中尽可能多的关于这个应用程序，不同控件，它接受的输入，以及它如何以合法方式执行的相关知识。
The goal of this step is to learn as much as possible about the application, the different components in it, the inputs it receives, and how it behaves when used in a legitimate manner.
可能这会迫使你丢弃所有的数据，或者学习一种新的输入的方式，或者放弃你目前正在用的其它四大技术，当然这可能并不是一个最好的开始。
If leaving forces you to leave all your data behind, or to learn a new way of typing, or to surrender four other technologies you were still using, then maybe this is not the best one to start.
在没有可分割的线形输入情况下，这是一个弱点，但如果输入是线形可分的，当更灵活的算法遇到更多的麻烦时，它可以强制学习。
This can be a weakness in cases where the input isn't actually linearly separable, but if the input is linearly separable, it can force learning when more flexible algorithms might have more trouble.
监管学习的任务是学习带标签的训练数据的功能，以便预测任何有效输入的值。
Supervised learning is tasked with learning a function from labeled training data in order to predict the value of any valid input.
监管学习的常见例子包括将电子邮件消息分类为垃圾邮件，根据类别标记网页，以及识别手写输入。
Common examples of supervised learning include classifying E-mail messages as spam, labeling Web pages according to their genre, and recognizing handwriting.
例如，某些基本的神经网络，它们的感知器只倾向于学习线形函数(通过划一条线可以把函数输入解析到分类系统中)。
For instance, a certain kind of basic neural network, the perceptron, is biased to learning only linear functions (functions with inputs that can be separated into classifications by drawing a line).
通过学习和记忆，建立输入和输出变量之间的非线性关系。
By studying and remembering, the nonlinear relationship of the input and output variable is established.
（现在网上有很多这样的参考文档，你在google搜索栏里输入‘你要学习的编程语言’+‘referencecard（参考卡片？？）’）
There are many reference cards available over internet. Type in 'language to learn' + 'reference card' in google.
在学习了本教程之后，您应该完全了解Groff的基本知识，包括如何编写和处理基本的Groff输入文件、以及如何从这些文件生成各种输出。
After taking this tutorial, you should have a complete understanding of Groff fundamentals, including how to write and process basic Groff input files and how to produce various output from them.
在前面对管道线的讨论中，您学习了如何接受一个命令的输出，并将它用作另一个命令的输入。
In the preceding discussion of pipelines, you learned how to take the output of one command and use it as input to another command.
CallXML学习起来非常轻松，并提供了对按键电话(touchtone)输入的支持(请注意，它并不支持语音识别)。
CallXML is extremely easy to learn and provides great support for touchtone input (note that it does not support voice recognition).
对于一个外语学习者来说，阅读是一种最重要的语言输入方式。
For a foreign language learner, reading is the most important way of language input.
该机器人用这些数据作为其机器学习算法的输入数据，产生一个脸部表情和相应肌肉马达运动之间的信息存储分布图。
The robot used this data as an input for its machine learning algorithms and created a map between its facial expressions and the movements of its muscle motors.
语言的输入和输出是相互依存的一个整体，是语言学习的完整过程。
It stresses that language input and output is a complete process of language learning, which is inseparable.
无所不在的鼠标输入设备没有任何隐喻；相反，是习惯用法的学习。
The ubiquitous mouse input device is not metaphoric of anything , but rather is learned idiomatically.
无所不在的鼠标输入设备没有任何隐喻；相反，是习惯用法的学习。
The ubiquitous mouse input device is not metaphoric of anything , but rather is learned idiomatically.
应用推荐