Publication

Geometric robustness of deep networks: analysis and improvement

Pascal Frossard, Seyed Mohsen Moosavi Dezfooli, Can Kanbak
2018
Conference Papers

Résumé

Deep convolutional neural networks have been shown to be vulnerable to arbitrary geometric transformations. However, there is no systematic method to measure the invariance properties of deep networks to such transformations. We propose ManiFool as a simple yet scalable algorithm to measure the invariance of deep networks. In particular, our algorithm measures the robustness of deep networks to geometric transformations in a worst-case regime as they can be problematic for sensitive applications. Our extensive experimental results show that ManiFool can be used to measure the invariance of fairly complex networks on high dimensional datasets and these values can be used for analyzing the reasons for it. Furthermore, we build on ManiFool to propose a new adversarial training scheme and we show its effectiveness on improving the invariance properties of deep neural networks.

Source officielle

https://infoscience.epfl.ch/entities/publication/9f98da17-2df4-4db4-b156-107706b0f84b

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, Can Kanbak
2018
Conference Papers

Résumé

Source officielle

https://infoscience.epfl.ch/entities/publication/9f98da17-2df4-4db4-b156-107706b0f84b

À propos de ce résultat

Concepts associés (23)

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.

Réseau de neurones à propagation avant

Un réseau de neurones à propagation avant, en anglais feedforward neural network, est un réseau de neurones artificiels acyclique, se distinguant ainsi des réseaux de neurones récurrents. Le plus connu est le perceptron multicouche qui est une extension du premier réseau de neurones artificiel, le perceptron inventé en 1957 par Frank Rosenblatt. vignette|Réseau de neurones à propagation avant Le réseau de neurones à propagation avant est le premier type de réseau neuronal artificiel conçu. C'est aussi le plus simple.

Types of artificial neural networks

There are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.

Afficher plus

Publications associées (30)

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Volkan Cevher, Grigorios Chrysos, Fanghui Liu

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

2024

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

Safe Deep Neural Networks

Kyle Michael Matoba

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

EPFL2024

Afficher plus