Defend Intelligence, content creator and engineer specialized in artificial intelligence, explains a word of innovation, one of today’s big technological trends: the machine learning.

Machine learning is a fast-growing field of application, which constitutes a set of methods, techniques and algorithms that allow complex Artificial Intelligence problems to be solved by learning from a large data set.

It is precisely machine learning that defines the algorithms for recommending movies, music, or even autonomous cars!

But how exactly does a machine learn?

Let’s take the example of house prices in a neighborhood.

We will present the machine with the prices of thousands of houses and their descriptions. Using machine learning algorithms, the computer will automatically learn the characteristics that make a house more or less expensive (surface area, location etc.). This is how the computer will deduce rules.

From this data and this learning, the computer will be able to predict the result, i.e. the price of a house.

Machine learning is an innovative approach because it radically changes the traditional way of coding (a human listing precise but subjective rules on a software that will calculate a result). Here, the machine, from the data at its disposal, deduces by itself adequate rules to answer the task. The choice is therefore theoretically more objective.

It is thus thanks to machine learning that we can create more and more powerful artificial intelligence rules!

Read also on Hello Future

AI set to revolutionize the study of animal behaviour


LightOn, a private and secure AI for businesses – Laurent Daudet

AI ethics

Ethics and AI: 2023 heralds “a Wild West era in generative AI”


Sensors and AI ensure the good health of bridges


Is AutoML the key to the democratization of machine learning?


Earthquake alerts: a convolutional neural network is monitoring the Earth’s gravity field


AI is facilitating the exploitation of the astronomical amount of space data


Behind the Scenes of AI — The Challenges and Methods of Explainability