Modèle génératif

vignette|Schéma représentant la différence entre un modèle discriminatif et un modèle génératif. En classement automatique un modèle génératif est un modèle statistique défini par opposition à un modèle discriminatif. Étant donné une variable X à laquelle il doit associer une autre variable Y, le modèle génératif cherchera à décrire la probabilité conditionnelle P(X|Y) ainsi que la probabilité P(Y) puis d'utiliser la formule de Bayes pour calculer la probabilité P(Y|X). Autrement dit le modèle génératif cherche à décrire chaque classe et à en déduire à quel point une donnée présente les caractéristiques de cette classe. Avantages et inconvénients Les avantages d'un modèle génératif sont les suivants :

Un modèle génératif permet d'estimer la confiance d'une prédiction et donc de formuler un rejet d'une prédiction, ce qui est impossible dans un modèle discriminatif.
La connaissance de P(X|Y) permet également de générer

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 (6)

Unités associées

Chargement

Concepts associés (17)

Concepts associés

Chargement

Cours associés (42)

Cours associés

Chargement

Séances de cours associées (87)

Séances de cours associées

Chargement

Apprentissage profond

L'apprentissage profond ou apprentissage en profondeur (en anglais : deep learning, deep structured learning, hierarchical learning) est un sous-domaine de l’intelligence artificiel

Modèle discriminatif

En classification automatique un modèle discriminatif est un modèle statistique qui, étant donné une variable X à laquelle il doit associer une autre variable Y, cherchera à décrire directement la pro

Apprentissage supervisé

L'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'

DH-406: Machine learning for DH

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 implement methods to analyze diverse data types, such as images, music and social network data.

EE-411: Fundamentals of inference and learning

This is an introductory course in the theory of statistics, inference, and machine learning, with an emphasis on theoretical understanding & practical exercises. The course will combine, and alternate, between mathematical theoretical foundations and practical computational aspects in python.

EE-608: Deep Learning For Natural Language Processing

The Deep Learning for NLP course provides an overview of neural network based methods applied to text. The focus is on models particularly suited to the properties of human language, such as categorical, unbounded, and structured representations, and very large input and output vocabularies.

CryoETGAN: Cryo-Electron Tomography Image Synthesis via Unpaired Image Translation

Chengkun Li, Min Xu

Cryo-electron tomography (Cryo-ET) has been regarded as a revolution in structural biology and can reveal molecular sociology. Its unprecedented quality enables it to visualize cellular organelles and macromolecular complexes at nanometer resolution with native conformations. Motivated by developments in nanotechnology and machine learning, establishing machine learning approaches such as classification, detection and averaging for Cryo-ET image analysis has inspired broad interest. Yet, deep learning-based methods for biomedical imaging typically require large labeled datasets for good results, which can be a great challenge due to the expense of obtaining and labeling training data. To deal with this problem, we propose a generative model to simulate Cryo-ET images efficiently and reliably: CryoETGAN. This cycle-consistent and Wasserstein generative adversarial network (GAN) is able to generate images with an appearance similar to the original experimental data. Quantitative and visual grading results on generated images are provided to show that the results of our proposed method achieve better performance compared to the previous state-of-the-art simulation methods. Moreover, CryoETGAN is stable to train and capable of generating plausibly diverse image samples.

FRONTIERS MEDIA SA2022

Chargement

On Linear Interpolation in the Latent Space of Deep Generative Models

Quentin Christian Becker, Mike Yan Michelis

The underlying geometrical structure of the latent space in deep generative models is in most cases not Euclidean, which may lead to biases when comparing interpolation capabilities of two models. Smoothness and plausibility of linear interpolations in latent space are associated with the quality of the underlying generative model. In this paper, we show that not all such interpolations are comparable as they can deviate arbitrarily from the shortest interpolation curve given by the geodesic. This deviation is revealed by computing curve lengths with the pull-back metric of the generative model, finding shorter curves than the straight line between endpoints, and measuring a non-zero relative length improvement on this straight line. This leads to a strategy to compare linear interpolations across two generative models. We also show the effect and importance of choosing an appropriate output space for computing shorter curves. For this computation we derive an extension of the pull-back metric.

2021

Chargement

Further results on latent discourse models and word embeddings

Youssef Allouah

We discuss some properties of generative models for word embeddings. Namely, (Arora et al., 2016) proposed a latent discourse model implying the concentration of the partition function of the word vectors. This concentration phenomenon led to an asymptotic linear relation between the pointwise mutual information (PMI) of pairs of words and the scalar product of their vectors. Here, we first revisit this concentration phenomenon and prove it under slightly weaker assumptions, for a set of random vectors symmetrically distributed around the origin. Second, we empirically evaluate the relation between PMI and scalar products of word vectors satisfying the concentration property. Our empirical results indicate that, in practice, this relation does not hold with arbitrarily small error. This observation is further supported by two theoretical results: (i) the error cannot be exactly zero because the corresponding shifted PMI matrix cannot be positive semidefinite; (ii) under mild assumptions, there exist pairs of words for which the error cannot be close to zero. We deduce that either natural language does not follow the assumptions of the considered generative model, or the current word vector generation methods do not allow the construction of the hypothesized word embeddings.

MICROTOME PUBL2021

Chargement