Tensorflow 简明教程

Understanding Artificial Intelligence

人工智能包括机器和特定计算机系统对人类智能进行模拟的过程。人工智能的示例包括学习、推理和自我纠正。人工智能的应用包括语音识别、专家系统、图像识别和机器视觉。

Artificial Intelligence includes the simulation process of human intelligence by machines and special computer systems. The examples of artificial intelligence include learning, reasoning and self-correction. Applications of AI include speech recognition, expert systems, and image recognition and machine vision.

机器学习是人工智能的一个分支，它处理能够学习任何新数据和数据模式的系统和算法。

Machine learning is the branch of artificial intelligence, which deals with systems and algorithms that can learn any new data and data patterns.

让我们关注以下提到的韦恩图来理解机器学习和深度学习概念。

Let us focus on the Venn diagram mentioned below for understanding machine learning and deep learning concepts.

venn diagram

机器学习包括机器学习的一部分，深度学习是机器学习的一部分。遵循机器学习概念的程序的能力是可以改善其观测数据执行。数据转换的主要动机是改进其知识，以便在未来实现更好的结果，为特定系统提供更接近所需输出的输出。机器学习包括“模式识别”，它包括在数据中识别模式的能力。

Machine learning includes a section of machine learning and deep learning is a part of machine learning. The ability of program which follows machine learning concepts is to improve its performance of observed data. The main motive of data transformation is to improve its knowledge in order to achieve better results in the future, provide output closer to the desired output for that particular system. Machine learning includes “pattern recognition” which includes the ability to recognize the patterns in data.

这些模式应该过训练以所需的方式显示输出。

The patterns should be trained to show the output in desirable manner.

机器学习可以用两种不同的方式进行训练−

Machine learning can be trained in two different ways −

  1. Supervised training

  2. Unsupervised training

Supervised Learning

监督式学习或监督式训练包括将训练集作为输入提供给系统的过程，其中每个示例都带有所需输出值的标签。通过最大程度减小特定损失函数（它表示输出错误相对于所需的输出系统）来执行此类型的训练。

Supervised learning or supervised training includes a procedure where the training set is given as input to the system wherein, each example is labeled with a desired output value. The training in this type is performed using minimization of a particular loss function, which represents the output error with respect to the desired output system.

在完成训练后，将通过训练集中的不相交示例（也称为验证集）来测量每个模型的准确性。

After completion of training, the accuracy of each model is measured with respect to disjoint examples from training set, also called the validation set.

supervised learning

“监督式学习”的最佳示例是一堆包含附加信息的图片。在这里，用户可以训练模型来识别新图片。

The best example to illustrate “Supervised learning” is with a bunch of photos given with information included in them. Here, the user can train a model to recognize new photos.

Unsupervised Learning

在无监督学习或无监督训练中，包括未通过系统标记他们所属类的训练示例。系统寻找具有共同特征的数据，并根据内部知识特征对其进行更改。这种类型的学习算法基本上用于聚类问题。

In unsupervised learning or unsupervised training, include training examples, which are not labeled by the system to which class they belong. The system looks for the data, which share common characteristics, and changes them based on internal knowledge features.This type of learning algorithms are basically used in clustering problems.

“无监督学习”的最佳示例是一堆没有包含信息的图片，用户使用分类和聚类对模型进行训练。这种类型的训练算法是基于假设的，因为没有提供信息。

The best example to illustrate “Unsupervised learning” is with a bunch of photos with no information included and user trains model with classification and clustering. This type of training algorithm works with assumptions as no information is given.

unsupervised learning