Modèles économiques des logiciels open sourcealt=Logo de l’Open Source Initiative : un disque vert dont on a enlevé une part en bas et un petit disque au centre|vignette|Logo de l’Open Source Initiative, association défendant le potentiel économique du développement de logiciels open source. alt=Logo de l’April : « promouvoir et défendre le logiciel libre »|vignette|Logo de l’April, association française faisant la promotion des logiciels libres et de leurs modèles économiques.
Situated learningSituated learning is a theory that explains an individual's acquisition of professional skills and includes research on apprenticeship into how legitimate peripheral participation leads to membership in a community of practice. Situated learning "takes as its focus the relationship between learning and the social situation in which it occurs". The theory is distinguished from alternative views of learning which define learning as the acquisition of propositional knowledge.
Q-learningvignette|400x400px|Dans le Q-learning, l'agent exécute une action a en fonction de l'état s et d'une fonction Q. Il perçoit alors le nouvel état s' et une récompense r de l'environnement. Il met alors à jour la fonction Q. Le nouvel état s' devient alors l'état s, et l'apprentissage continue. En intelligence artificielle, plus précisément en apprentissage automatique, le Q-learning est un algorithme d'apprentissage par renforcement. Il ne nécessite aucun modèle initial de l'environnement.
Hierarchical organizationA hierarchical organization or hierarchical organisation (see spelling differences) is an organizational structure where every entity in the organization, except one, is subordinate to a single other entity. This arrangement is a form of a hierarchy. In an organization, the hierarchy usually consists of a singular/group of power at the top with subsequent levels of power beneath them. This is the dominant mode of organization among large organizations; most corporations, governments, criminal enterprises, and organized religions are hierarchical organizations with different levels of management, power or authority.
Organisation horizontaleA flat organization (also known as horizontal organization or flat hierarchy) is an organizational structure with few or no levels of middle management between staff and executives. An organizational structure refers to the nature of the distribution of the units and positions within it, and also to the nature of the relationships among those units and positions. Tall and flat organizations differ based on how many levels of management are present in the organization and how much control managers are endowed with.
Meta-learning (computer science)Meta learning is a subfield of machine learning where automatic learning algorithms are applied to metadata about machine learning experiments. As of 2017, the term had not found a standard interpretation, however the main goal is to use such metadata to understand how automatic learning can become flexible in solving learning problems, hence to improve the performance of existing learning algorithms or to learn (induce) the learning algorithm itself, hence the alternative term learning to learn.
Théorie de l'apprentissageLearning theory describes how students receive, process, and retain knowledge during learning. Cognitive, emotional, and environmental influences, as well as prior experience, all play a part in how understanding, or a worldview, is acquired or changed and knowledge and skills retained. Behaviorists look at learning as an aspect of conditioning and advocate a system of rewards and targets in education.
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.
Histoire du logiciel libreLhistoire du logiciel libre est intimement imbriquée avec celle de l'informatique et celle du génie logiciel. Elle ne commence en tant que telle qu'à partir du moment où est apparu le besoin de distinguer le logiciel libre du logiciel propriétaire, selon le principe énoncé pour Le Cru et le Cuit. Ces prémices datant de la fin du , il ne peut s'agir d'une discipline académique. L'histoire du logiciel libre est donc présentée ici de façon informelle. thumb|Manipulation des nombres sur un boulier.
Apprentissage ensemblisteIn statistics and machine learning, ensemble methods use multiple learning algorithms to obtain better predictive performance than could be obtained from any of the constituent learning algorithms alone. Unlike a statistical ensemble in statistical mechanics, which is usually infinite, a machine learning ensemble consists of only a concrete finite set of alternative models, but typically allows for much more flexible structure to exist among those alternatives.
