In machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task.
Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, video, and sensor data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms.
Feature learning can be either supervised, unsupervised or self-supervised.
In supervised feature learning, features are learned using labeled input data. Labeled data includes input-label pairs where the input is given to the model and it must produce the ground truth label as the correct answer. This can be leveraged to generate feature representations with the model which result in high label prediction accuracy. Examples include supervised neural networks, multilayer perceptron and (supervised) dictionary learning.
In unsupervised feature learning, features are learned with unlabeled input data by analyzing the relationship between points in the dataset. Examples include dictionary learning, independent component analysis, matrix factorization and various forms of clustering.
In self-supervised feature learning, features are learned using unlabeled data like unsupervised learning, however input-label pairs are constructed from each data point, which enables learning the structure of the data through supervised methods such as gradient descent. Classical examples include word embeddings and autoencoders. SSL has since been applied to many modalities through the use of deep neural network architectures such as CNNs and transformers.
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.
Deep Learning (DL) is the subset of Machine learning reshaping the future of transportation and mobility. In this class, we will show how DL can be used to teach autonomous vehicles to detect objects,
This course aims to introduce the basic principles of machine learning in the context of the digital humanities. We will cover both supervised and unsupervised learning techniques, and study and imple
Machine learning and data analysis are becoming increasingly central in sciences including physics. In this course, fundamental principles and methods of machine learning will be introduced and practi
Le cours suivi propose une initiation aux concepts de base de la programmation impérative tels que : variables, expressions, structures de contrôle, fonctions/méthodes, en les illustrant dans la synta
Le cours suivi propose une introduction aux concepts de base de la programmation orientée objet tels que : encapsulation et abstraction, classes/objets, attributs/méthodes, héritage, polymorphisme, ..
Ce cours initie à la programmation en utilisant le langage C++. Il ne présuppose pas de connaissance préalable. Les aspects plus avancés (programmation orientée objet) sont donnés dans un cours suivan
Le partitionnement en k-moyennes (ou k-means en anglais) est une méthode de partitionnement de données et un problème d'optimisation combinatoire. Étant donnés des points et un entier k, le problème est de diviser les points en k groupes, souvent appelés clusters, de façon à minimiser une certaine fonction. On considère la distance d'un point à la moyenne des points de son cluster ; la fonction à minimiser est la somme des carrés de ces distances.
En apprentissage automatique, un réseau de neurones convolutifs ou réseau de neurones à convolution (en anglais CNN ou ConvNet pour convolutional neural networks) est un type de réseau de neurones artificiels acycliques (feed-forward), dans lequel le motif de connexion entre les neurones est inspiré par le cortex visuel des animaux. Les neurones de cette région du cerveau sont arrangés de sorte qu'ils correspondent à des régions qui se chevauchent lors du pavage du champ visuel.
In machine learning, a deep belief network (DBN) is a generative graphical model, or alternatively a class of deep neural network, composed of multiple layers of latent variables ("hidden units"), with connections between the layers but not between units within each layer. When trained on a set of examples without supervision, a DBN can learn to probabilistically reconstruct its inputs. The layers then act as feature detectors. After this learning step, a DBN can be further trained with supervision to perform classification.
Explore la prévision des trajectoires dans les véhicules autonomes, en mettant l'accent sur les modèles d'apprentissage profond pour prédire les trajectoires humaines dans les scénarios de transport socialement conscients.
Explore des modèles générateurs pour la prévision de trajectoires dans les véhicules autonomes, y compris des modèles discriminatifs vs générateurs, VAES, GANS, et des études de cas.
Couvre les fondamentaux des réseaux neuronaux multicouches et de l'apprentissage profond, y compris la propagation arrière et les architectures réseau comme LeNet, AlexNet et VGG-16.
Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...
EPFL2024
, ,
In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches have shown remarkable success on synthetic datasets, we have observed them to fail in the presence of real-world data. We ...
Monitoring the health of complex industrial assets is crucial for safe and efficient operations. Health indicators that provide quantitative real-time insights into the health status of industrial assets over time serve as valuable tools for, e.g., fault d ...