What is Machine Learning? Explain the difference between deep learning / artificial intelligence and machine learning

Machine learning is to make a machine learn data so that it can deal with various problems. It is attracting attention as one of the technologies responsible for the "learning" of AI.
The learning methods of machine learning are roughly classified into three types: "supervised learning", "unsupervised learning", and "reinforcement learning".
In this article, we explain the meaning of machine learning, the types of learning methods, and the differences from deep learning in an easy-to-understand manner.

What is machine learning?

First, let's check the meaning of machine learning, what you can do with machine learning, and the difference from AI and deep learning.

Meaning of machine learning

Machine learning is "learning" in AI. It has the meaning of "learning by the machine itself" just as humans learn.

In short, the purpose of machine learning is to ensure that a trained machine can do more than what is programmed by the programmer.

Although often spoken at the same time as "AI" and "deep learning," machine learning is one of the technologies that support AI, and deep learning is one of the methods of machine learning.

Why machine learning is attracting attention

Machine learning is also deeply related to fields such as AI and big data, which are attracting attention in DX promotion

The feature of machine learning is to process a huge amount of information and find features and rules in the data. You will be able to predict and judge things based on the derived features and rules.

In short, machine learning is being used to empower AI to learn and to process and analyze big data with large amounts of complex data.

Explains three learning methods of machine learning

Machine learning can be broadly divided into three categories: supervised learning, unsupervised learning, and reinforcement learning. Here, let's explain each mechanism.

① Supervised learning

Supervised learning is learning artificial intelligence in one direction by giving a set of examples and model answers (teacher signals). Generally, a large amount of data is required, and the neural network itself judges the correctness of the output result based on the given data.

It is possible to make judgments and actions by guessing from the examples even for cases that have not been learned, but it has the disadvantage that it cannot respond to unknown events that humans cannot be given knowledge in advance. In addition, there is a limit to the ability to "be smarter than the person who gave the model answer."

It is used for sales forecasting using "regression" that derives trends (functions) based on past data and predicts future numerical values, and image classification using "classification" that automatically classifies unknown data. increase.

② Unsupervised learning

Unsupervised learning does not require a model answer, and AI accumulates data based on its own activities and learns by itself.

It is a learning method that does not require a large amount of data, but instead, an "environment where you can learn correctly" is important. It is necessary to assume that the environment is consistent, and it is not possible to learn about events that cannot be simulated.

It is used for recommendations and customer segmentation utilizing "clustering" that analyzes accumulated data and extracts and groups similar ones from many.

③ Reinforcement learning

Reinforcement learning is a learning method in which AI repeats trial and error in its own environment to find the optimal behavior and value. In terms of recognizing and analyzing the results of AI's actions, it can be regarded as unsupervised learning.

An important factor in reinforcement learning is to make AI firmly aware of its own actions and situations. Then, the evaluation value for the result in the placed environment is used as a "reward" as a clue for learning.

For example, let's say you give AI an environment to play a game. Since there are no teachers, it does not show its strength at the beginning, but AI itself considers "how can I get more rewards" for each match. Data will be accumulated and become stronger with each battle.

In this way, reinforcement learning has a wide range of applications and is very effective when the object to be learned cannot be modeled.

The difference between machine learning and deep learning

Deep learning is one of the machine learning methods. As long as there is sufficient training data, it is possible to automatically extract the characteristics of the data using a neural network.

Deep learning makes it possible to learn unstructured data (images, natural language, sound) that was previously difficult to digitize.

In addition, the increased variation of digitization has made it possible to generate natural language and detect anomalies, improving the accuracy of optimization and recommendations.

Programming language "Python" used in AI (artificial intelligence) development

"Python" is the standard programming language used in AI development.

The main reason is that the code is easy to handle among many programming languages and it is suitable for processing big data required for machine learning. In addition to being easy to perform scientific and technological calculations, it is also useful because it has a library for machine learning.

Compared to other languages, it is easier for beginners to learn programming, and the AI boom is also attracting attention.