機器學習初學者

In recent times, we hear these few things a lot:

最近，我們經常聽到以下幾件事：

First is —The COVID-19 Pandemic, of course! Second is — Quarantine and the Third is “Machine Learning’’. Yes, Machine Learning is so much in hype these days and no doubt that it is a technology of the future. Machine Learning, Artificial Intelligence, Data Science, etc are the pioneers of futuristic applications. Thus, in this article, we’ll talk about Machine Learning: What it is, How it works, at the beginner level!

首先是-COVID-19大流行，當然！ 第二是“隔離”，第三是“機器學習”。 是的，如今機器學習大肆宣傳，毫無疑問，它是未來的技術。 機器學習，人工智能，數據科學等是未來應用程序的先驅。 因此，在本文中，我們將討論機器學習：它是什么，它是如何工作的，在初學者級別！

So let’s start.

因此，讓我們開始吧。

Image provided by Author圖片由作者提供

So first, let’s look into What is Machine Learning?

首先，讓我們看看什么是機器學習？

Machine Learning is a subset of Artificial Intelligence and is defined as,

機器學習是人工智能的子集，定義為：

“The study of computer algorithms that improve automatically through experience”

“ 通過經驗自動改進的計算機算法的研究 ”

Before we move ahead, let’s see how Tom Mitchell defines Machine Learning:

在繼續進行之前，讓我們看看Tom Mitchell如何定義機器學習：

“A well-posed learning problem is defined as, A computer program is said to learn from experience E with respect to some task T and some performance measure P if its performance on T as measured by P improves with experience E ”

“ 一個恰當的學習問題被定義為，一個計算機程序被認為可以從經驗E中學習一些任務T和一些績效指標P，如果它對P的績效(由P衡量)隨經驗E的提高而有所改善，那么， ”

Ok, I know, both the definitions might sound a bit overwhelming at the moment. Thus let’s see in simple terms how it works so that you will be able to appreciate their definitions. So in simple terms, what is a Machine Learning Algorithm?

好的，我知道，這兩個定義目前可能聽起來有些不知所措。 因此，讓我們簡單地看一下它是如何工作的，以便您能夠欣賞它們的定義。 簡單來說，什么是機器學習算法？

It’s like a child’s brain. When the kid is young you show him/her an Apple and tell that this is Apple. If you repeat this a few times, it establishes a connection with the child’s brain in order to recognize an Apple.

就像孩子的大腦。 當孩子年幼時，您可以給他/她一個蘋果，并告訴他這是蘋果。 如果重復幾次，它將與孩子的大腦建立聯系以識別蘋果。

Suppose, next time the kid see’s an Apple he might be able to recognize an apple using its features such as color, size, shape, category, etc.

假設，下次孩子看到一個蘋果時，他也許可以使用其顏色，大小，形狀，類別等功能識別一個蘋果。

Now, when we talk about machine learning, replace the child’s brain by a machine learning model, and replace the apple with some data.

現在，當我們談論機器學習時，用機器學習模型替換孩子的大腦，并用一些數據替換蘋果。

Thus, this is Machine Learning at a very basic level and this is how it works. Now, once you read the above definitions again, this time you would surely be able to understand and appreciate them.

因此，這是非常基礎的機器學習，這就是它的工作方式。 現在，一旦您再次閱讀以上定義，您肯定可以理解和欣賞它們。

Now that we know that what is Machine Learning and how it works, let’s look at the steps in Machine Learning:

現在我們知道什么是機器學習及其工作原理，下面讓我們看一下機器學習中的步驟：

• Data Collection
  數據采集
• Data Preparation
  資料準備
• Choosing a Model
  選擇模型
• Training a Model
  訓練模型
• Evaluating a Model
  評估模型
• Parameter tuning
  參數調整
• Implementation
  實作

Thus, for a machine learning model, Data is an important aspect. From data collection to preparation for choosing and training the model makes machine learning algorithms.

因此，對于機器學習模型而言， 數據是重要的方面。 從數據收集到準備選擇和訓練模型，機器學習算法都可以使用。

Thus, let’s talk about the types of machine learning algorithms. At the most basic level, there are three types of learning:

因此，讓我們討論一下機器學習算法的類型。 在最基本的層次上，有三種學習類型：

1)監督學習 (1) Supervised Learning)

Supervised learning as the name indicates the presence of a supervisor as a teacher. Basically supervised learning is a learning in which we teach or train the machine using data that is well labeled which means some data is already tagged with the correct answer. After that, the machine is provided with a new set of examples (data) so that the supervised learning algorithm analyses the training data (set of training examples) and produces a correct outcome from labeled data.

監督學習的名稱表示主管是教師。 基本上，監督學習是一種學習，我們在學習中使用標記正確的數據來教學或訓練機器，這意味著某些數據已被正確答案標記。 之后，機器會提供一組新的示例(數據)，以便監督學習算法分析訓練數據(一組訓練示例)并從標記的數據中產生正確的結果。

2)無監督學習 (2) Unsupervised Learning)

Unsupervised learning is the training of machines using information that is neither classified nor labeled and allowing the algorithm to act on that information without guidance. Here the task of the machine is to group unsorted information according to similarities, patterns, and differences without any prior training of data.

無監督學習是使用既未分類也未標記的信息來訓練機器，并允許算法在沒有指導的情況下對信息進行操作。 在這里，機器的任務是根據相似性，模式和差異對未分類的信息進行分組，而無需事先訓練數據。

Unlike supervised learning, no teacher is provided, which means no training will be given to the machine. Therefore the machine is restricted to find the hidden structure in unlabeled data by ourselves.

與監督學習不同，它不提供任何老師，這意味著不會對機器進行任何培訓。 因此，機器只能自己尋找未標記數據中的隱藏結構。

3)強化學習 (3) Reinforcement Learning)

Reinforcement learning is an area of Machine Learning. It is about taking suitable action to maximize reward in a particular situation. It is employed by various software and machines to find the best possible behavior or path it should take in a specific situation.

強化學習是機器學習的一個領域。 它是關于采取適當的措施以在特定情況下最大化回報。 它被各種軟件和機器所采用，以找到在特定情況下應采取的最佳行為或路徑。

Reinforcement learning differs from the supervised learning in a way that in supervised learning the training data has the answer key with it so the model is trained with the correct answer itself, whereas in reinforcement learning, there is no answer but the reinforcement agent decides what to do to perform the given task. In the absence of a training dataset, it is bound to learn from its experience.

強化學習與監督學習的不同之處在于，在監督學習中，訓練數據具有答案鍵，因此可以使用正確的答案本身對模型進行訓練，而在強化學習中，沒有答案，而是由強化代理決定要做什么。執行給定的任務。 在沒有訓練數據集的情況下，它必然會從其經驗中學習。

This is all about Machine Learning that you should know to get started with it.

這是關于機器學習的全部知識，您應該從入門開始就應該知道這一點。

What are your thoughts on machine learning and is it overhyped? Curious to know in the comments…

您對機器學習有什么看法，是否被夸大了？ 好奇地在評論中知道...

翻譯自: https://medium.com/programminghero/machine-learning-for-absolute-beginners-d04e2e704e7

機器學習初學者

總結

以上是生活随笔為你收集整理的机器学习初学者_绝对初学者的机器学习的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。