Publication

Empirical study of the topology and geometry of deep networks

Pascal Frossard, Seyed Mohsen Moosavi Dezfooli, Alhussein Fawzi
2018
Conference Papers

Résumé

The goal of this paper is to analyze the geometric properties of deep neural network image classifiers in the input space. We specifically study the topology of classification regions created by deep networks, as well as their associated decision boundary. Through a systematic empirical study, we show that state-of-the-art deep nets learn connected classification regions, and that the decision boundary in the vicinity of datapoints is flat along most directions. We further draw an essential connection between two seemingly unrelated properties of deep networks: their sensitivity to additive perturbations of the inputs, and the curvature of their decision boundary. The directions where the decision boundary is curved in fact characterize the directions to which the classifier is the most vulnerable. We finally leverage a fundamental asymmetry in the curvature of the decision boundary of deep nets, and propose a method to discriminate between original images, and images perturbed with small adversarial examples. We show the effectiveness of this purely geometric approach for detecting small adversarial perturbations in images, and for recovering the labels of perturbed images.

Source officielle

https://infoscience.epfl.ch/entities/publication/f5464f3b-1c35-4df1-8415-3c084e418d43

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.

Pascal Frossard, Seyed Mohsen Moosavi Dezfooli, Alhussein Fawzi
2018
Conference Papers

Résumé

Source officielle

https://infoscience.epfl.ch/entities/publication/f5464f3b-1c35-4df1-8415-3c084e418d43

À propos de ce résultat

Concepts associés (14)

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 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.

Deep belief network

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.

Réseau neuronal convolutif

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.

Afficher plus

Publications associées (31)

Understanding generalization and robustness in modern deep learning

Maksym Andriushchenko

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

EPFL2024

Random matrix methods for high-dimensional machine learning models

Antoine Philippe Michel Bodin

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

EPFL2024

Residual-based attention in physics-informed neural networks

Nikolaos Stergiopoulos, Sokratis Anagnostopoulos

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

Elsevier Science Sa2024

Afficher plus