« Back to Glossary Index

Deep learning is a subset of machine learning in which complex models called Neural Networks are employed. The term «deep» stems from the fact that these models are composed of multiple layers stacked on top of each other (hidden layers) and in each layer, a specific data transformation and weight adjustment is applied. The weights, in particular, play a crucial role as they constitute the values to be optimised during training. Unlike classical machine learning, deep learning requires processing the training set multiple times (epochs), and after each pass, the weights are updated using the Backpropagation algorithm. This process continues until the model achieves satisfactory performance.Today, applications of deep learning span various domains such as Computer Vision, Natural Language Processing (NLP) and Large Language Models (LLMs).