There are several techniques owned by machine learning, but broadly ML has two basic learning techniques, namely supervised and unsupervised. In order to know more about computer vision datasets, you can visit our website.
Supervised Learning
Supervised learning technique is a technique that you can apply to machine learning that can receive information that already exists in the data by giving certain labels. It is hoped that this technique can provide a target for the output carried out by comparing past learning experiences. Suppose you have a number of films that you have labeled with a certain category. You also have movies with comedy categories including 21 Jump Street and Jumanji movies. Besides that, you also have other categories, such as horror film categories such as The Conjuring and It. When you buy a new film, you identify the genre and content of the film. After the film is identified then you will save the film in the appropriate category.
Unsupervised Learning
Unsupervised learning techniques are techniques that you can apply to machine learning that is used on data that does not have information that can be applied directly. It is hoped that this technique can help find hidden structures or patterns in unlabeled data. Slightly different from supervised learning, you do not have any data that will be used as a reference beforehand. Suppose you have never bought a movie at all, but at one time, you bought a number of movies and want to divide them into several categories so that they are easy to find. Of course you will identify which films are similar. In this case, suppose you identify based on the genre of the film. For example, if you have the Conjuring film, then you will save the Conjuring film in the horror film category.
How machine learning actually works varies according to what kind of learning technique or method you use in ML. But basically the principle of how machine learning works is still the same, including data collection, data exploration, model or technique selection, providing training to the selected model and evaluating the results of ML.
