Although the concepts of Machine Learning and Artificial Intelligence are often confused and used interchangeably, with a certain tendency to use the term Artificial Intelligence to refer to both scientific fields, the reality is that they refer to different areas of knowledge. In this article we are going to see the differences between both concepts, as well as with other common related terms, such as Big Data or Deep Learning.
There are several definitions of the concept of Machine Learning, one of the most popular being the following:
Machine Learning is a branch of Artificial Intelligence that aims to build systems that automatically learn from data.
From this definition we can extract two vital characteristics of the Machine Learning field:
Let's take an example: Let's imagine that we want to create a system that learns to recognize whether a certain image represents a cat (the image will be labeled as a 1) or anything else (the image will be labeled as a 0), as we can see in the following image.
When building a Machine Learning model, the developer does not tell the model what patterns to look for in order to recognize a cat, such as pointed ears, four legs, fur all over the body with certain characteristics... but the model itself, based on the history of images provided, will decide which characteristics are more useful to distinguish a cat from other types of entities. This is what we refer to as "automatic" learning, and it is what defines Machine Learning systems.
Therefore, we have made it clear that Machine Learning is a subset within all the techniques covered by the field of Artificial Intelligence, specifically a subset that is defined by the ability to learn automatically to solve certain tasks.
There are other concepts related to Machine Learning that are often confused and not always well used, such as Deep Learning and Big Data.
On the one hand, we have Deep Learning, which refers to a specific family of Machine Learning models. This family of models has special characteristics that make it especially suitable for certain problems, such as image recognition, but they are still a type of Machine Learning techniques. If you are interested in deepening in the concept of Deep Learning, we have an article on this topic here.
Secondly, the term Big Data is also commonly used in connection with Machine Learning. However, it is important to be clear that it refers to a concept that, although related to Machine Learning, is independent and has different characteristics. Simply put, Big Data refers to very large and complex data sets, often from non-classical data sources. These datasets are so voluminous that traditional data processing software simply cannot handle them, but they enable business problems to be solved, often by training Machine Learning models on these Big Data sets, which previously could not have been addressed.
In short, Machine Learning is a subset within the area of Artificial Intelligence. In turn, Deep Learning is a subset of the models available within Machine Learning techniques. Finally, Big Data refers to large data sets, which allow to increase the potential and usefulness of Machine Learning models.
