Apprentissage profond

Résumé

L'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. Durant les années 2000, ces progrès ont suscité des investissements privés, universitaires et publics importants, notamment de la part des GAFAM (Google, Apple, Facebook, Amazon, Microsoft). Définition L'apprentissage profond est un type d'apprentissage automatique ou qui repose sur l’apprentissage de représentations de données par opposition à des algorithmes, qui sont sp

Source officielle

https://fr.wikipedia.org/wiki/Apprentissage_profond

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 (118)

Personnes associées

Chargement

Unités associées (49)

Unités associées

Chargement

Concepts associés (115)

Concepts associés

Chargement

Cours associés (104)

Cours associés

Chargement

Séances de cours associées (291)

Séances de cours associées

Chargement

inspectors that walk over the track and check the defects on the rail surface, fasteners and sleepers. In the case of concrete sleepers, rail inspectors classify defects according to their size and occurrence over 20 sleepers. The manual inspection is error prone, it is time consuming and it can be sometimes risky. In an eort to overcome these issues, SBB has developed a project called AISI (Articial Intelligence Streckeninspection) in order to automatize the rail inspection by collecting and analysing images with diagnosis trains equipped with cameras. The objective of this thesis is integrated within the AISI Project, since its goal is the conception of a deep learning model to detect and classify concrete sleepers defects using computer vision and more specically, object detection. The defects studied in this thesis are cracks and akings (or spallings). In the literature, many researchers have tackled the subject of defect detection in concrete, especially in civil infrastructures. The most common methods a combination of image-processing and Machine Learning (image pre-processing and a classier) whereas the latest methods use deep learning (CNN, FCN and RPN, YOLO). The proposed methodology uses a Fast-RCNN model developed with Tensor ow Object Detection API. The evaluation of the model is given on a total of 996 defects and its precision and recall are given. The model shows average results as the number of false positives is high. It has been noted that the labels provided needed to be improved. The proposed approach has a great potential of development since a large amount of training data can be added thanks to the produced relabelling process. Also, the designed pipeline establishes a base that can be adjustable for various algorithms and congurations.

2021

Chargement

Identifying nuclei is often a critical first step in analyzing microscopy images of cells and classical image processing algorithms are most commonly used for this task. Recent developments in deep learning can yield superior accuracy, but typical evaluation metrics for nucleus segmentation do not satisfactorily capture error modes that are relevant in cellular images. We present an evaluation framework to measure accuracy, types of errors, and computational efficiency; and use it to compare deep learning strategies and classical approaches. We publicly release a set of 23,165 manually annotated nuclei and source code to reproduce experiments and run the proposed evaluation methodology. Our evaluation framework shows that deep learning improves accuracy and can reduce the number of biologically relevant errors by half. (c) 2019 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

WILEY2019

Chargement

Deep Learning for Music: Similarity Search and Beyond

Matthieu Gaston Michel Albert Devaux

This paper is a study on the use of Machine Learning and Deep Learning to determine the similarity between different musics. The first part introduces the framework used and some concepts of Deep Learning that will be used in the algorithms. The second part talks about the problem caused by the topic and how the models should be to be efficient. The third part describes the algorithms used for trying to solve this problem. The fourth part is the analysis and testing of the model, followed by the conclusion to be drawn from them.

2019

Chargement