EnResNet: ResNets Ensemble via the Feynman--Kac Formalism for Adversarial Defense and Beyond

DOI10.1137/19M1265302MaRDI QIDQ5037566

Binjie Yuan, Bao Wang, Zuoqiang Shi, Stanley J. Osher

Publication date: 1 March 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1811.10745

zbMATH Keywords

convection-diffusion equationFeynman-Kac formuladeep learningadversarial defense

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items

Accuracy and architecture studies of residual neural network method for ordinary differential equations, Deep learning via dynamical systems: an approximation perspective

Uses Software

• CIFAR
• ImageNet
• Adam
• GitHub
• torchdiffeq
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Adversarial defense via the data-dependent activation, total variation minimization, and adversarial training
• A proposal on machine learning via dynamical systems
• Stable architectures for deep neural networks
• Graph interpolating activation improves both natural and robust accuracies in data-efficient deep learning
• The relative performance of ensemble methods with deep convolutional neural networks for image classification
• On Distributions of Certain Wiener Functionals