LEARNING PROBLEM 中文是什么意思 - 中文翻译

• 学习问题

在 英语 中使用 Learning problem 的示例及其翻译为 中文

How to formulate a basic reinforcement Learning problem?
如何制定基本的强化学习问题？?

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

So because you don't have enough data to solve this end-to-end learning problem.
因为没有足够的数据去解决端到端的学习问题，.

DDPG can solve the reinforcement learning problem in continuous action space.
DDPG可以解决连续行动空间上的强化学习问题。

In general, a learning problem considers a set of n samples of data and then tries to predict properties of unknown data.
一般来说，学习问题考虑了一组n个数据样本，然后尝试预测未知数据的属性。

DDPG can solve the reinforcement learning problem in continuous action space.
本文将DQN应用在连续行动空间的强化学习问题上。

This is an example of binary- or two-class- classification, an important and widely applicable kind of machine learning problem.
这是一个典型的二分类问题，是一种重要且广泛适用的机器学习问题。

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

A key function to help transform time series data into a supervised learning problem is the Pandas shift() function.
将时间序列数据转换成有监督学习问题的一个关键是Pandas的shift()函数。

This is a supervised learning problem, known as a regression problem, because the outcome measurement is quantitative.
这是一个监督学习的问题，也称之为回归问题，因为结果测量是可量化的．.

If you have labeled data, you know, with spam and non-spam e-mail, we would treat this as a Supervised Learning problem.
如果你有标记好的数据，区别好是垃圾还是非垃圾邮件，我们把这个当作监督学习问题。

We will use a simple sequence learning problem to demonstrate the TimeDistributed layer.
我们将使用一个简单的序列学习问题来演示TimeDistributed层。

If the solution implies to optimize an objective function by interacting with an environment, it's a reinforcement learning problem.
如果想通过与环境互动来优化一个目标函数，那就是强化学习问题。

Every extra attribute makes the learning problem twice as hard, and that's just with Boolean attributes.
每个额外的属性都会把学习问题的困难程度加倍，而这也只是有布尔属性的情况。

In this video, I would like to start talking about a second type of unsupervised learning problem called dimensionality reduction.
这个视频，我想开始谈论第二种类型的无监督学习问题，称为降维。

Let's assume that in our machine learning problem, the features x have sufficient information with which we can use to predict y accurately.
机器学习问题中，特征值x包含了足够的信息，这些信息可以帮助我们用来准确地预测y，.

This is an example of binary- or two-class- classification, an important and widely applicable kind of machine learning problem.
这是一个二元（binary）或者二分类问题，一种重要且应用广泛的机器学习问题。

Matrix completion is a basic machine learning problem that has wide applications, especially in collaborative filtering and recommender systems.
矩阵完成是一个基本的机器学习问题，具有广泛的应用，特别是在协同过滤和推荐系统中。

This is an example of binary- or two-class- classification, an important and widely applicable kind of machine learning problem.
这是一个二元分类（又称为两类分类）的示例，也是一种重要且广泛适用的机器学习问题。

With any reinforcement learning problem(especially with a board game), you need a way of evaluating the environment, or the current board position.
对于任何强化学习的问题（尤其是在棋盘游戏中），我们都需要一种评估当前环境或者说当前位置的方法。

When the target variable that we're trying to predict is continuous, the learning problem is also called a regression problem..
当我们试图预测的目标变量是连续的，比如在我们的房屋例子中，我们叫该学习问题是一个回归问题。

Text recognition in a natural environment like cities, roads and businesses is a challenging computer vision(CV) and machine learning problem.
在城市、道路和商户等自然环境中做文本识别，这是一个具有挑战性的计算机视觉和机器学习问题。

The learning problem is characterized by observations comprised of input data and output data and some unknown but coherent relationship between the two.
学习问题的特点是由输入数据和输出数据组成的观察(observations)以及两者之间的未知但一致的关系。

Bayesian method is also highly scalable, requiring a number of parameters linear in the number of variables(features/predictors) in a learning problem.
朴素贝叶斯分类器具有高度可扩展性，在学习问题中需要多个变量（特征/预测器）数量的线性参数。

Explore the basics of solving a classification-based machine learning problem, and get a comparative study of some of the current most popular algorithms.
学习有关解决基于分类的机器学习问题的基础知识，并对当前最受欢迎的一些算法进行比较研究。

Naive Bayes classifiers are highly scalable, requiring a number of parameters linear in the number of variables(features/predictors) in a learning problem.
朴素贝叶斯分类器具有高度可扩展性，在学习问题中需要多个变量（特征/预测器）数量的线性参数。

To understand how to solve a reinforcement learning problem, let's go through a classic example of reinforcement learning problem- Multi-Armed Bandit Problem..
为了了解如何解决强化学习问题，我们将分析一个强化学习问题的经典例子--多摇臂老虎机问题。

When the target variable that we're trying to predict is continuous, such as in our housing example, we call the learning problem a regression problem..
当我们试图预测的目标变量是连续的，比如在我们的房屋例子中，我们叫该学习问题是一个回归问题。

To understand how to solve a reinforcement learning problem, let's go through a classic example of reinforcement learning problem- Multi-Armed Bandit Problem..
为了理解如何去解决一个强化学习问题，让我们通过一个经典的例子来说明一下强化学习问题--多臂赌博机。