Exploration de données

Résumé

L’exploration de données, connue aussi sous l'expression de fouille de données, forage de données, prospection de données, data mining, ou encore extraction de connaissances à partir de données, a pour objet l’extraction d'un savoir ou d'une connaissance à partir de grandes quantités de données, par des méthodes automatiques ou semi-automatiques. Elle se propose d'utiliser un ensemble d'algorithmes issus de disciplines scientifiques diverses telles que les statistiques, l'intelligence artificielle ou l'informatique, pour construire des modèles à partir des données, c'est-à-dire trouver des structures intéressantes ou des motifs selon des critères fixés au préalable, et d'en extraire un maximum de connaissances. L'utilisation industrielle ou opérationnelle de ce savoir dans le monde professionnel permet de résoudre des problèmes très divers, allant de la gestion de la relation client à la maintenance préventive, en passant par la détection de fraudes ou encore l'optimisation de sites

Source officielle

https://fr.wikipedia.org/wiki/Exploration_de_donn%C3%A9es

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (100)

Publications associées

Chargement

Personnes associées (25)

Personnes associées

Chargement

Unités associées (16)

Unités associées

Chargement

Concepts associés (140)

Concepts associés

Chargement

Cours associés (86)

Cours associés

Chargement

Séances de cours associées (208)

Séances de cours associées

Chargement

2018

Chargement

Expectation propagation in the large data limit

Guillaume Philippe Ivan Joseph Dehaene

Expectation propagation (EP) is a widely successful algorithm for variational inference. EP is an iterative algorithm used to approximate complicated distributions, typically to find a Gaussian approximation of posterior distributions. In many applications of this type, EP performs extremely well. Surprisingly, despite its widespread use, there are very few theoretical guarantees on Gaussian EP, and it is quite poorly understood. To analyse EP, we first introduce a variant of EP: averaged EP, which operates on a smaller parameter space. We then consider averaged EP and EP in the limit of infinite data, where the overall contribution of each likelihood term is small and where posteriors are almost Gaussian. In this limit, we prove that the iterations of both averaged EP and EP are simple: they behave like iterations of Newton's algorithm for finding the mode of a function. We use this limit behaviour to prove that EP is asymptotically exact, and to obtain other insights into the dynamic behaviour of EP, e.g. that it may diverge under poor initialization exactly like Newton's method. EP is a simple algorithm to state, but a difficult one to study. Our results should facilitate further research into the theoretical properties of this important method.

Wiley2018

Chargement

In recent years, ontology for the Product Lifecycle Management domain has raised a lot of interest in research communities, both academic and industrial. It has emerged as a convenient method for supporting the concept of closed lifecycle information loop, which is one of the most important issues of PLM. By modeling relevant aspects collected from all lifecycle stages of a product, within one ontology, a common knowledge structure is created accessible to all actors. Assuming that appropriate mechanisms for updating ontology (or rather, instances that populate it) are provided, ontology becomes a base layer for a knowledge management platform. Useful experience and information from all productsâ life-cycle stages, can influence designerâs decisions and business strategies. The industrial research community has recognized this added value of ontological implementation, and there is an increasing number of developed ontologies for this purpose. Application of ontology contributes to time efficiency by reducing the time required to retrieve information. Furthermore, it allows for the enhancement of design decisions which are supported through additional information at the appropriate moment. Finally, ontology gives an overall perspective on a product's lifecycle, allowing from-the-top optimization. Different domains modeled in ontology, and software platforms that use them as a base layer, become interoperable and convenient to merge. The purpose of ontology as it is today is not to store data, for the most part because there are more efficient data base systems to handle large data amounts. Still, the domain modeled within ontology is composed of structured and un-structured data sets, and ontology itself can give us a top view on relations and dependences between these data sets. In this perspective, it holds a strong similarity to a relational data base, if relations in the data base where defined so that they depicted the real world in the most precise possible manner. In large companies today, handling a growing amount of data generated every day is becoming an increasingly relevant problem. Managing and storing them, although challenging, is still feasible, but holding data without understanding it carries little added value. In an effort to exploit useful information contained in unstructured data sources, a number of decision support systems and enterprise resource planning systems have been developed. They can be very diverse in functionality and efficiency but the one thing that they all have in common is that the user has to be the one making the initiative and defining the queries. This means that the user has to know which information he is looking for, or hoping to extract. As a consequence, the number of relevant correlations and dependencies between different factors of real life captured in the data are left unnoticed, simply because they were not assumed. In the PLM domain, this is particularly present since it involves a number of actors and most of them are interacting only with a small subset of domain concepts. Data mining as a discipline, gives a number of tools for resolving this issue. All of the algorithms are designed to detect correlations, underlying patterns or functions that generated the data. The problem of data mining techniques is that they are still performed mostly manually. Although deterministic steps of data mining procedures can be supported by existing software tools, the others remain an obstac

EPFL2015

Chargement

EPFL2015