Experiential learningExperiential learning (ExL) is the process of learning through experience, and is more narrowly defined as "learning through reflection on doing". Hands-on learning can be a form of experiential learning, but does not necessarily involve students reflecting on their product. Experiential learning is distinct from rote or didactic learning, in which the learner plays a comparatively passive role. It is related to, but not synonymous with, other forms of active learning such as action learning, adventure learning, free-choice learning, cooperative learning, service-learning, and situated learning.
Robotique en essaimLa robotique en essaim est une branche de la robotique appliquant les méthodes d'intelligence distribuée aux systèmes à plusieurs robots. Il s'agit généralement d'utiliser des robots simples, voire simplistes, et peu coûteux, d'un intérêt individuel assez limité, mais qui ensemble (par exemple via des capacités d'autoassemblage ou d'auto-organisation) forment un système complexe et robuste. La robotique en essaim cherche à étudier la conception et le comportement des robots.
Bio-inspired roboticsBio-inspired robotic locomotion is a fairly new subcategory of bio-inspired design. It is about learning concepts from nature and applying them to the design of real-world engineered systems. More specifically, this field is about making robots that are inspired by biological systems, including Biomimicry. Biomimicry is copying from nature while bio-inspired design is learning from nature and making a mechanism that is simpler and more effective than the system observed in nature.
Modèle discriminatifDiscriminative models, also referred to as conditional models, are a class of logistical models used for classification or regression. They distinguish decision boundaries through observed data, such as pass/fail, win/lose, alive/dead or healthy/sick. Typical discriminative models include logistic regression (LR), conditional random fields (CRFs) (specified over an undirected graph), decision trees, and many others. Typical generative model approaches include naive Bayes classifiers, Gaussian mixture models, variational autoencoders, generative adversarial networks and others.
Developmental roboticsDevelopmental robotics (DevRob), sometimes called epigenetic robotics, is a scientific field which aims at studying the developmental mechanisms, architectures and constraints that allow lifelong and open-ended learning of new skills and new knowledge in embodied machines. As in human children, learning is expected to be cumulative and of progressively increasing complexity, and to result from self-exploration of the world in combination with social interaction.
Apprentissage superviséL'apprentissage supervisé (supervised learning en anglais) est une tâche d'apprentissage automatique consistant à apprendre une fonction de prédiction à partir d'exemples annotés, au contraire de l'apprentissage non supervisé. On distingue les problèmes de régression des problèmes de classement. Ainsi, on considère que les problèmes de prédiction d'une variable quantitative sont des problèmes de régression tandis que les problèmes de prédiction d'une variable qualitative sont des problèmes de classification.
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.
Legged robotLegged robots are a type of mobile robot which use articulated limbs, such as leg mechanisms, to provide locomotion. They are more versatile than wheeled robots and can traverse many different terrains, though these advantages require increased complexity and power consumption. Legged robots often imitate legged animals, such as humans or insects, in an example of biomimicry. Legged robots, or walking machines, are designed for locomotion on rough terrain and require control of leg actuators to maintain balance, sensors to determine foot placement and planning algorithms to determine the direction and speed of movement.
Concept (philosophie)En logique, un concept est un contenu de pensée, qui, lorsqu'il est appliqué à un objet, peut former une proposition. En linguistique, le concept représente le signifié, c'est-à-dire le sens du mot, tandis que le mot lui-même constitue son signifiant. Le concept est un terme abstrait qui se distingue donc de la chose désignée par ce concept. Le terme lui-même est introduit au Moyen Âge (conceptus) par Thomas d'Aquin puis Guillaume d'Ockham et les autres philosophes scolastiques .
Learning spaceLearning space or learning setting refers to a physical setting for a learning environment, a place in which teaching and learning occur. The term is commonly used as a more definitive alternative to "classroom," but it may also refer to an indoor or outdoor location, either actual or virtual. Learning spaces are highly diverse in use, configuration, location, and educational institution. They support a variety of pedagogies, including quiet study, passive or active learning, kinesthetic or physical learning, vocational learning, experiential learning, and others.
Atlas (robot)vignette|Vue de face du robot Atlas en 2013. Atlas est un robot de type androïde principalement développé par Boston Dynamics, sous financement et surveillance de la Defense Advanced Research Projects Agency (DARPA). Il mesure 1,88 m et est conçu pour diverses tâches de recherche et sauvetage, il a été dévoilé au public le . Le développement d'Atlas fait partie du Darpa Robotics Challenge. En 2016, une vidéo présentant une évolution du robot est diffusée par Boston Dynamics.
Apprentissage profondL'apprentissage profond ou apprentissage en profondeur (en anglais : deep learning, deep structured learning, hierarchical learning) est un sous-domaine de l’intelligence artificielle qui utilise des réseaux neuronaux pour résoudre des tâches complexes grâce à des architectures articulées de différentes transformations non linéaires. Ces techniques ont permis des progrès importants et rapides dans les domaines de l'analyse du signal sonore ou visuel et notamment de la reconnaissance faciale, de la reconnaissance vocale, de la vision par ordinateur, du traitement automatisé du langage.
