LEARNING PROBLEM - 翻译成中文

• 学习问题

在 英语 中使用 Learning problem 的示例及其翻译为 中文

Unfortunately, we cannot always tell whether a given learning problem is realizable, because the true function is not known.
不幸的是，我们不能总是判断一个给定的学习问题是否可以实现，因为真正的函数是未知的。

The first two of these problems could be considered planning problems(since some form of model is available), while the last one could be considered to be a genuine learning problem.
前两个问题可以被考虑为规划问题，而最后一个问题可以被认为是genuinelearning问题。

We will use a one hot encoding to represent the learning problem for the LSTM.
我们将使用一个有效编码来表示LSTM的学习问题。

Researchers have developed an artificial neural network made out of DNA that can solve a classic machine learning problem: correctly identifying handwritten numbers.
加州理工学院的研究人员开发了一种由DNA制成的人工神经网络，可以解决一个经典的机器学习问题：正确识别手写数字。

If we have unlabeled data and want to find structure, it's an unsupervised learning problem.
如果是无标签数据，想找到结构，那就是非监督学习问题。

In this post, I want to share with you the skeleton of my process for working a machine learning problem.
在这篇文章中，我想和大家分享我的机器学习问题过程的框架。

If you have unlabelled data and want to find structure, it's an unsupervised learning problem.
如果您有未标记的数据并且想要查找结构，那么这是一个无监督的学习问题。

Applied machine learning is the development of a learning system to address a specific learning problem.
应用型机器学习是一个学习系统(learingsystem)的发展，以解决一个特定的学习问题。

Here we really faced a machine learning problem,” said Kouider.
在这里，我们确实面临着一个机器学习的问题，”Kouider说。

If it's unlabeled data with the purpose of finding structure, it's an unsupervised learning problem.
如果您有未标记的数据并且想要查找结构，那么这是一个无监督的学习问题。

We can formulate the semi-supervised learning problem on this toy graph as follows: predict a color(“red” or“blue”) for every node in the graph.
我们可以将这个简单图的半监督学习问题描述成：预测图中每个节点的颜色（红色或蓝色）。

The challenge is, it's difficult to orchestrate and optimize a deep learning problem across many servers, because the faster GPUs run, the faster they learn..
挑战在于，在许多服务器上编排和优化一个深度学习问题是很困难的，因为GPU运行得越快，它们学习的速度就越快。

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.
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。

I have said it before, working machine learning problems is addictive.
我之前说过，处理机器学习的问题是会让人上瘾的。

Refresher courses for teachers of pupils with learning problems.
教授有学习问题儿童的教师的复习课程.

Learning problems and attention deficits.
学习困难与注意缺陷。

In most Supervised Machine Learning problems we need to define a model and estimate its parameters based on a training dataset.
在大多数监督性机器学习问题中，我们需要定义一个模型并基于训练数据集预估其参数。

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.
机器学习也与优化密切相关：许多学习问题被公式化为训练集的一些损失函数的最小化。

Here, based on our specific machine learning problems, we apply useful algorithms like regressions, decision trees, random forests, etc.
这里，基于具体的机器学习问题，我们要应用有效的算法，如回归，决策树，随机森林等。

After a brief overview of different machine learning problems, we discuss linear regression, its objective function and closed-form solution.
在简要地概述各种机器学习问题后，我们讨论线性回归，它的目标函数和闭合解。