Validation croiséeLa validation croisée () est, en apprentissage automatique, une méthode d’estimation de fiabilité d’un modèle fondée sur une technique d’échantillonnage. Supposons posséder un modèle statistique avec un ou plusieurs paramètres inconnus, et un ensemble de données d'apprentissage sur lequel on peut apprendre (ou « entraîner ») le modèle. Le processus d'apprentissage optimise les paramètres du modèle afin que celui-ci corresponde le mieux possible aux données d'apprentissage.
Adversarial machine learningAdversarial machine learning is the study of the attacks on machine learning algorithms, and of the defenses against such attacks. A survey from May 2020 exposes the fact that practitioners report a dire need for better protecting machine learning systems in industrial applications. To understand, note that most machine learning techniques are mostly designed to work on specific problem sets, under the assumption that the training and test data are generated from the same statistical distribution (IID).
Algorithme d'apprentissage incrémentalEn informatique, un algorithme d'apprentissage incrémental ou incrémentiel est un algorithme d'apprentissage qui a la particularité d'être online, c'est-à-dire qui apprend à partir de données reçues au fur et à mesure du temps. À chaque incrément il reçoit des données d'entrées et un résultat, l'algorithme calcule alors une amélioration du calcul fait pour prédire le résultat à partir des données d'entrées.
Automated machine learningAutomated machine learning (AutoML) is the process of automating the tasks of applying machine learning to real-world problems. AutoML potentially includes every stage from beginning with a raw dataset to building a machine learning model ready for deployment. AutoML was proposed as an artificial intelligence-based solution to the growing challenge of applying machine learning. The high degree of automation in AutoML aims to allow non-experts to make use of machine learning models and techniques without requiring them to become experts in machine learning.
Invariant estimatorIn statistics, the concept of being an invariant estimator is a criterion that can be used to compare the properties of different estimators for the same quantity. It is a way of formalising the idea that an estimator should have certain intuitively appealing qualities. Strictly speaking, "invariant" would mean that the estimates themselves are unchanged when both the measurements and the parameters are transformed in a compatible way, but the meaning has been extended to allow the estimates to change in appropriate ways with such transformations.
