Intelligence artificielle distribuéeL'Intelligence Artificielle Distribuée (IAD) est une branche de l'Intelligence artificielle. On distinguera : le principe d'adapter les approches de l'Intelligence Artificielle classique sur une architecture distribuée (par exemple avec une parallélisation des programmes) les approches où l'Intelligence Artificielle est conceptuellement répartie sur un certain nombre d'entités (réseaux de neurones artificiels, systèmes multi-agents) de façon similaire à une Intelligence distribuée.
Topic modelvignette|Visualisation du résumé d'un article scientifique traité par topic model. L'intensité de la couleur varie selon la probabilité d'appartenir au topic en question. En apprentissage automatique et en traitement automatique du langage naturel, un topic model (modèle thématique ou « modèle de sujet ») est un modèle probabiliste permettant de déterminer des sujets ou thèmes abstraits dans un document. Analyse sémantique latente (LSA) Allocation de Dirichlet latente (LDA) Analyse sémantique latente probab
Coordinate descentCoordinate descent is an optimization algorithm that successively minimizes along coordinate directions to find the minimum of a function. At each iteration, the algorithm determines a coordinate or coordinate block via a coordinate selection rule, then exactly or inexactly minimizes over the corresponding coordinate hyperplane while fixing all other coordinates or coordinate blocks. A line search along the coordinate direction can be performed at the current iterate to determine the appropriate step size.
Apprentissage PACL'apprentissage PAC (pour probably approximately correct en anglais) est un cadre théorique pour l'apprentissage automatique. Il permet notamment d'évaluer la difficulté d'un problème dans le contexte de l'apprentissage supervisé. Il a été proposé par Leslie Valiant en 1984. Dans le cadre de l'apprentissage PAC, l'algorithme «apprenant» reçoit des données d'apprentissage («samples») et doit choisir une fonction qui généralise ces données. Cette fonction est choisie parmi un ensemble préétabli.
Computational learning theoryIn computer science, computational learning theory (or just learning theory) is a subfield of artificial intelligence devoted to studying the design and analysis of machine learning algorithms. Theoretical results in machine learning mainly deal with a type of inductive learning called supervised learning. In supervised learning, an algorithm is given samples that are labeled in some useful way. For example, the samples might be descriptions of mushrooms, and the labels could be whether or not the mushrooms are edible.
Sparse dictionary learningSparse dictionary learning (also known as sparse coding or SDL) is a representation learning method which aims at finding a sparse representation of the input data in the form of a linear combination of basic elements as well as those basic elements themselves. These elements are called atoms and they compose a dictionary. Atoms in the dictionary are not required to be orthogonal, and they may be an over-complete spanning set. This problem setup also allows the dimensionality of the signals being represented to be higher than the one of the signals being observed.
Intelligence artificielle dans la santévignette|Rayon X d'une main, avec calcul automatique de l'âge osseux par un logiciel informatique. L'intelligence artificielle (IA) dans la santé est l'utilisation d'algorithmes et de logiciels pour s'approcher de la cognition humaine dans l'analyse de données médicales complexes. Plus précisément, l'IA est la capacité des algorithmes informatiques à tirer des conclusions sans intervention humaine directe. L'objectif principal des applications des IA dans le domaine de la santé est d'analyser les relations entre, d'une part, la prévention ou les traitements et, d'autre part, l'état de santé des patients.
Predictive codingIn neuroscience, predictive coding (also known as predictive processing) is a theory of brain function which postulates that the brain is constantly generating and updating a "mental model" of the environment. According to the theory, such a mental model is used to predict input signals from the senses that are then compared with the actual input signals from those senses. With the rising popularity of representation learning, the theory is being actively pursued and applied in machine learning and related fields.
Labeled dataLabeled data is a group of samples that have been tagged with one or more labels. Labeling typically takes a set of unlabeled data and augments each piece of it with informative tags. For example, a data label might indicate whether a photo contains a horse or a cow, which words were uttered in an audio recording, what type of action is being performed in a video, what the topic of a news article is, what the overall sentiment of a tweet is, or whether a dot in an X-ray is a tumor.
Random fieldIn physics and mathematics, a random field is a random function over an arbitrary domain (usually a multi-dimensional space such as ). That is, it is a function that takes on a random value at each point (or some other domain). It is also sometimes thought of as a synonym for a stochastic process with some restriction on its index set. That is, by modern definitions, a random field is a generalization of a stochastic process where the underlying parameter need no longer be real or integer valued "time" but can instead take values that are multidimensional vectors or points on some manifold.
