Robust Large Margin Deep Neural Networks

DOI10.1109/TSP.2017.2708039zbMath1414.68076arXiv1605.08254MaRDI QIDQ4621805

Miguel R. D. Rodrigues, Guillermo Sapiro, Jure Sokolić, Raja Giryes

Publication date: 8 February 2019

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1605.08254

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Understanding generalization error of SGD in nonconvex optimization, An analysis of training and generalization errors in shallow and deep networks, Stable parameterization of continuous and piecewise-linear functions, Improved spectral norm regularization for neural networks, The role of mutual information in variational classifiers, Generalization Error in Deep Learning, A tight upper bound on the generalization error of feedforward neural networks, Adversarial noise attacks of deep learning architectures: stability analysis via sparse-modeled signals, Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness, On the Purity and Entropy of Mixed Gaussian States, Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators