L’entraînement est le processus qui utilise des données et un algorithme d’apprentissage pour déterminer ou améliorer les paramètres d’un modèle. Pendant l’entraînement, le système ajuste des valeurs internes telles que les poids, les points de séparation ou les biais afin que ses sorties correspondent mieux à la tâche visée.
The process of determining the ideal parameters (weights and biases) comprising a model. During training, a system reads in examples and gradually adjusts parameters. Training uses each example anywhere from a few times to billions of times. See Supervised Learning in the Introduction to ML course for more information.
Training is the process of presenting a set of data examples to an AI system in order to refine its model. The AI system can improve how it works by analyzing the training data, making predictions, and comparing those predictions against the actual outcome. Then, the AI system uses that information to tune the model to improve accuracy.
The process of identifying a model for a given training data set. For a linear model, this means finding the weights. For a tree, it involves identifying the split points.