Federated learning is a machine learning technique that allows multiple devices or systems to collaborate in training a centralised model without having to share their sensitive data. In federated learning, devices or systems keep their data private and only share model parameters among themselves.
This technique is useful in situations where sensitive data cannot be shared, for example, when working with medical or financial data. Instead of collecting all data in one place to train a model, federated learning allows data to be kept on local devices or systems, ensuring data privacy.
Federated learning is used in a variety of applications, such as speech recognition, fraud detection and personalised recommendation. For example, in speech recognition, federated learning allows multiple personal devices to participate in training a centralised speech recognition model, which improves the accuracy of the model without compromising the privacy of users' personal data.
In the previous articles ("Basic concepts to build a commercial software with artificial intelligence" and "How to materialize the opportun [...]
Read More »The financial sector is constantly implementing new technologies to modernize and digitize its functions. One of the reasons for this is the processing of [...]
Read More »The commercial optimization software based on artificial intelligence must have feedback of the commercial actions carried out, of the nu [...]
Read More »Before explaining what artificial intelligence is, we would like to start with a sentence from the book Age of intelligent machines (1992), by Raymond Ku [...]
Read More »
