神码ai人工智能写作机器人_机器学习简介part1与人工智能的比较

最新推荐文章于 2025-07-16 17:55:35 发布

翻译最新推荐文章于 2025-07-16 17:55:35 发布 · 2.6k 阅读

CC 4.0 BY-SA版权

原文链接：https://medium.com/enjoy-algorithm/introduction-to-machine-learning-part1-comparison-with-artificial-intelligence-261d834254f

文章标签：

#人工智能 #机器学习 #python #深度学习

本文介绍了机器学习的基础概念，包括其定义、重要性、起源及应用领域。通过与人工智能的对比，帮助读者理解机器学习的独特之处及其发展历程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

神码ai人工智能写作机器人

Image for post — https://www.eastwestbank.com/ReachFurther/en/News/) https://www.eastwestbank.com/ReachFurther/en/News/ )

In this article we will try to learn every basic thing that one should know about the most fascinating and emerging technology these days, named as Machine learning. After reading this article, we will be able to answer the most fundamental questions like

在本文中，我们将尝试学习有关当今最有趣和新兴技术的每一项基本知识，它们被称为机器学习。阅读本文后，我们将能够回答最基本的问题，例如

本文的主要内容是：(Key takeaways from this article would be :)

1. What is Machine Learning ?2. Why do we need Machine Learning ?3. When did it start ? What is the history of Machine Learning?4. Where can we use Machine Learning ?

1.什么是机器学习？2。为什么我们需要机器学习？3。什么时候开始？机器学习的历史是什么？4。我们在哪里可以使用机器学习？

So, let’s begin our journey towards knowing this beautiful technology and find the answer of four W’s ( What, Why, When and Where ).

因此，让我们开始着手了解这项美丽技术的过程，并找到4个W的答案(什么，为什么，何时和何地)。

Before proceeding any further, have you ever thought how our brain works ?

在继续进行之前，您是否想过我们的大脑如何工作？

Let’s start from here itself.

让我们从这里开始。

Indeed brain is the most complex part of our body, knowledge about its working principle is still a big research that is underway. To explain the most complex part of the human body in a simple way, we can say that brain cells have perceptrons named Dendrites which receives the electrical signals coming from the entire body and responds to those signals through the Axon terminals.

的确，大脑是人体最复杂的部分，关于其工作原理的知识仍在进行中。为了以简单的方式解释人体最复杂的部分，我们可以说脑细胞具有名为Dendrites的感知器，该感知器接收来自整个人体的电信号并通过Axon终端对这些信号做出响应。

Whenever any known or similar set of inputs received from dendrites, it gives the similar set of actions as outputs through axons. Saying more explicitly, it learns the mapping function from input set to the output set.

每当从树突中收到任何已知或相似的输入集时，它都会给出与轴突输出相似的动作集。更明确地说，它学习从输入集到输出集的映射功能。

Taking analogy from the brain cells, if we try to represent brain cell functioning using bubbles, we can make a structure as shown in the figure below . And you know what, this structure is called Neural Network of Machine Learning.

从脑细胞进行类比，如果我们尝试使用气泡来表示脑细胞的功能，我们可以构建如下图所示的结构。您知道什么，这种结构称为机器学习神经网络。

Now, let’s learn the definition of Machine Learning, which will help us to answer our first W, which is :What is Machine Learning?

现在，让我们学习机器学习的定义，它将帮助我们回答第一个W：什么是机器学习？

Machine learning is the science of getting computers to act without being explicitly programmed.

机器学习是使计算机在不经过明确编程的情况下运行的科学。

Let’s know the Wikipedia definition as well,

让我们也知道维基百科的定义，

Machine Learning is a field of computer science that gives computers the ability to learn without being explicitly programmed.

机器学习是计算机科学的一个领域，它使计算机无需进行显式编程即可学习。

Did you notice something similar in between these two definitions ? To understand the similarity in a better way,

您是否注意到这两个定义之间有相似之处？为了更好地了解相似性，

Let’s first know what is traditional programming?

首先让我们知道传统编程是什么？

In traditional programming, we basically write functions as our program for our computer and whenever we pass some input to those functions, they produce corresponding outputs.

在传统编程中，我们基本上将函数编写为计算机程序，并且每当将某些输入传递给这些函数时，它们就会产生相应的输出。

But, in Machine learning, computer takes Data and Output as its input parameters and tries to produce the best suitable function that maps Data to Outputs. So basically, computer is learning a mapping function which maps the input data to the output data (Similar to the functioning of brain).

但是，在机器学习中，计算机将数据和输出作为其输入参数，并尝试产生将数据映射到输出的最合适的功能。因此，基本上，计算机正在学习将输入数据映射到输出数据的映射功能(类似于大脑的功能)。

Now you must be able to understand that why both the famous definitions included the statement, without explicitly programming the computer, ML provides computers, the ability to learn. Its because, we do not write the programs for our computer, it automatically learns the program based on the historical data.

现在您必须能够理解，为什么两个著名的定义都包含了该语句，而无需对计算机进行显式编程，ML却为计算机提供了学习的能力。 这是因为我们不为计算机编写程序，而是根据历史数据自动学习程序。

Now, we know “what machine learning is?” Shouldn’t we ask ourselves, Why?
Why do we need machine learning?

现在，我们知道“什么是机器学习？” 我们不应该自问，为什么？ 为什么我们需要机器学习？

We all know that computer programs are used for automation. And for this automation, Software Engineer is a very highly paid post in almost all software firms ranging from Google to newly formed small startups.

我们都知道计算机程序用于自动化。对于这种自动化，软件工程师是几乎所有软件公司(从Google到新成立的小型创业公司)的高薪职位。

So if a computer program is automation then Machine Learning is automating the process of automation. And that’s why we need machine learning. So we successfully found the answer of our second W (Why ML?).

因此，如果计算机程序是自动化的，那么机器学习将使自动化过程自动化。这就是为什么我们需要机器学习。因此，我们成功找到了第二个W(为什么是ML？)的答案。

“A breakthrough in machine learning would be worth ten Microsofts.”

“机器学习方面的突破将使十个微软值得。”

— Bill Gates, Former Chairman, Microsoft

—微软前董事长比尔·盖茨

To know everything about anything, we must know how actually it started? So let’s continue our journey towards finding the answer of our third W, which is

要了解一切，我们必须知道它是如何开始的？因此，让我们继续寻找第三个W的答案的过程，即

When did it start? What is the History of Machine Learning?

什么时候开始？ 机器学习的历史是什么？

In 1950’s, Arthur Samuel of IBM invented a program for the Game of Checkers. Based on the idea of rewards given (in terms of points) to the computers when they win the game or play a rational move. He came up with the name of “Machine Learning” in 1952.

在1950年代，IBM的Arthur Samuel发明了“跳棋游戏”程序。基于当计算机赢得游戏或进行合理移动时给予计算机奖励(以点数计)的想法。他在1952年提出了“机器学习”的名称。

After that, in 1957, Frank Rosenblatt developed the first successful neuro-computer with the name of Mark 1 Perceptron which was originally intended to be a custom-built hardware machine instead of a software program for Image recognition.

之后，在1957年，弗兰克·罗森布拉特(Frank Rosenblatt)开发了第一台成功的神经计算机，名称为Mark 1 Perceptron ，其最初旨在用作定制的硬件机器，而不是用于图像识别的软件程序。

Due to its resemblance to biological neurons, it created a hype in the public. People were so optimistic and hence in 1958, NewYork Times published

由于它与生物神经元相似，因此在公众中引起了炒作。人们是如此乐观，因此在1958年，《纽约时报》发表了

“the Navy [has] revealed the embryo of an electronic computer today that it expects will be able to walk, talk, see, write, reproduce itself and be conscious of its existence.”

“海军今天已经揭示了一台电子计算机的雏形，它希望它将能够行走，交谈，看到，书写，复制自己并意识到它的存在。”

But sooner, people noticed the shortcomings of the idea when it failed to learn the simple XOR function. They tried stacking many layers of mark-1 perceptron together (multilayer perceptron) to make the model stronger which did not work.

但是很快，当人们无法学习简单的XOR函数时，人们就注意到了这个想法的缺点。他们尝试将多层mark-1感知器(多层感知器)堆叠在一起，以使模型更坚固，无法正常工作。

Later in 1970’s or earlier 1980’s, Machine Learning and Artificial Intelligence took separate paths. But today also, many of us think that both of them (AI & ML) are same. Picturing the Venn diagram of Artificial Intelligence and Machine Learning, we can clearly see that ML is just a subset of AI.

在1970年代后期或1980年代初期，机器学习和人工智能采取了各自的道路。但是今天，我们中的许多人也认为两者(AI和ML)是相同的。描绘人工智能和机器学习的维恩图，我们可以清楚地看到ML只是AI的一个子集。

Let’s quickly know the definition of Artificial Intelligence so that we can correlate more easily.

让我们快速了解人工智能的定义，以便我们可以更轻松地进行关联。

Artificial intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions.

人工智能(AI)是指在被编程为像人一样思考并模仿其行为的机器中对人类智能进行仿真。

So, If any program senses the environment and takes hard-coded (based on human behaviour) decisions then it’s Artificial Intelligence. For example, suppose an autonomous car if fitted with LIDAR sensor which detects the distance of vehicle from obstacles. And there is an algorithm which applies brakes based on some function which takes input of distance. There is no learning involved in this entire process. Hence this is not a Machine Learning but yes this is Artificial Intelligence, because this is imitating the human intelligence.

因此，如果任何程序能够感知环境并做出硬编码(基于人类行为)的决策，那么它就是人工智能。例如，假设自动驾驶汽车装有LIDAR传感器，该传感器可检测车辆与障碍物之间的距离。并且存在一种算法，该算法基于一些需要输入距离的功能来施加制动。在整个过程中没有学习。因此，这不是机器学习，而是人工智能，因为这是在模仿人类的智能。

People started utilising the known information about the input sets which resulted into the growth of Artificial Intelligence. At that time, multilayer perceptrons needed very high computational power and because of which, whole research of machine learning became idle. It gained popularity again in 1990’s when million times faster computers came into existence.

人们开始利用有关输入集的已知信息，这导致了人工智能的发展。那时，多层感知器需要非常高的计算能力，因此，整个机器学习的研究变得空洞。它在1990年代再次流行，当时计算机的速度提高了数百万倍。

In 2012, after the discovery of AlexNet architecture ( A Neural Network Architecture named after its discoverer, Alex), it showed the tremendous potential and never lost the popularity henceforth.

在2012年发现AlexNet体系结构(一种以发现者Alex命名的神经网络体系结构)之后，它展现了巨大的潜力，并且从此从未失去其流行性。

Now at this stage of our journey, we have answered successfully the three Ws (What, Why and When) of Machine learning.

现在，在旅程的这个阶段，我们已经成功地回答了机器学习的三个方面(什么，为什么和什么时候)。

To wrap up quickly, let’s quickly find the answer of fourth W, which is

为了快速总结，让我们快速找到第四个W的答案，即

Where can we use this technology of Machine Learning ?

我们在哪里可以使用这种机器学习技术？

To give you some coolest examples where ML can play a vital role, let’s see some applications.

为了给您一些最有趣的示例，其中ML可以发挥至关重要的作用，让我们看一些应用程序。

机器学习的一些应用 (Some Applications of Machine Learning)

Robotics : Autonomous Bots, Self-driving cars et. Finance : Evaluation of risk on credit offers, Decision to invest money. E-commerce : Prediction of inventory stocks, Predicting and Suggesting similar products Biology : Drug design based on past experience ChatBots : Translators, Human voice recognition

机器人技术：自动机器人，自动驾驶汽车等。 财务：评估信贷风险，决定投资资金。 电子商务：库存预测，类似产品的预测和建议生物学：基于过去经验的药物设计聊天机器人：翻译，语音识别

一些与机器学习有关的令人震惊的事实。(Some mind blowing facts related to machine learning.)

Google’s AlphGo , a machine learning based program, beat 18-time world champion Lee Sedol in chess game.
Google的基于机器学习的程序AlphGo在国际象棋比赛中击败了18届世界冠军Lee Sedol 。
Sophia, a humanoid robot and a citizen of Saudi Arabia, is based on Machine learning and Artificial Intelligence.
Sophia是类人机器人，是沙特阿拉伯的公民，它基于机器学习和人工智能。
Machine Learning algorithms can predict the lung cancer in its earliest stage based on detailed images.
机器学习算法可以根据详细图像预测肺癌的最早阶段。
A company used ML algorithm for Code anonymization. They had 600 programmers, took 8 code samples from each and algorithm was able to predict who wrote the code with 83% accuracy. Imaging how useful this could be whenever there will be any Ransomware attacks.
某公司使用ML算法进行代码匿名化。他们有600名程序员，每个程序员都有8个代码示例，算法能够预测谁编写该代码的准确率达到83％。想象一下，无论何时有任何勒索软件攻击，这可能有多大用处。