机器学习问题 - 翻译成英语

• machine learning problems
• machine learning problem

在 中文 中使用 机器学习问题 的示例及其翻译为 英语

微软创建了分布式机器学习工具包，它让机器学习问题能够在多台电脑间有效配置。
Microsoft creates the“Distributed Machine Learning Toolkit”, which allows the efficient distribution of machine learning problems on multiple computers.

通过这个指南，我相信你能够更好地处理机器学习问题并从中积累经验。
Through this guide, I will enable you to work on machine learning problems and gain from experience.

在这段视频中，我要定义可能是最常见一种机器学习问题：那就是监督学习。
In this video, I'm going to define what is probably the most common type of Machine Learning problem, which is Supervised Learning..

使用强化学习的方法，这两种规划问题都可以被转化为机器学习问题。
Under a reinforcement learning methodology both planning problems would be converted to machine learning problems.

在监督机器学习问题中，我们通常有一个由许多$(x,y)$数据对组成的数据集$D$，然后试图去为下面的分布建模：.
In supervised machine learning problems, we often consider a dataset D of observation pairs(x, y) and we try to model the following distribution.

然后你将学习使用亚马逊的机器学习来解决更简单的一类机器学习问题，而亚马逊的SageMaker来解决更复杂的问题。
Then you will learn to use Amazon Machine Learning to solve a simpler class of machine learning problems, and Amazon SageMaker to solve more complex problems.”.

它先容了ApacheSpark的历史以及如何使用Python、RDD/Dataframes/Datasets安装它，然后通过解决机器学习问题，对自己的常识点进行查漏补缺。
It covers the history of Apache Spark, how to install it using Python, RDD/Dataframes/Datasets and then rounds-up by solving a machine learning problem.

推荐的方法来解决机器学习问题是：.
The recommended approach to solving machine learning problems is.

但是，也有过于依赖机器学习问题。
But, there are also problems with relying too heavily on the machine learning.

它可以应用于其他机器学习问题，如功能配置。
It can be applied to other machine learning problems such as function fitting.

许多数据科学家都看到了很酷的新机器学习问题。
Many data scientists see a cool new machine learning problem.

涉及序列的最简单的机器学习问题是一对一问题。
The simplest machine learning problem involving a sequence is a one to one problem..

然而，并不是所有的机器学习问题都必须从头开始解决。
Not every machine learning problem has to be solved from scratch, however.

以下是用于解决机器学习问题的工作流程的高度概述：.
Here's a high-level overview of the workflow used to solve machine learning problems.

此外，它们还用于分类以及监督机器学习问题中的回归。
Also, they are used for classification as well as the regression in supervised machine learning problems.

许多现实中的机器学习问题都可以归纳为这一类。
Many of the realistic-world machine learning related problems fall into this category.

其他机器学习问题，例如聚类，可以使用其他独特的量子算法。
Other machine learning problems, such as clustering, have uniquely quantum algorithms.

统计：统计的基础知识是进行任何机器学习问题所必需的。
Statistics: The basics of statistics are required for going forward with any machine learning problem.

从概念上来说，这是一个经典的机器学习问题。
On its face, this is a classic machine learning classification problem.

与大多数的机器学习问题类似，我们还是需要一个学习速率。
Similar to most machine learning problems, we will need a learning rate as well.