Regularizing neural network classification using random perturbations (A09)

• Subject Area: Mathematics
• Term: since 2022
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 442047500

Classification via trained deep neural networks is often very sensitive to adversarial noise on the input. We will investigate several approaches for increasing the robustness of deep learning models including randomized smoothing, randomness on the network parameters and constraints on the parameters during training. We aim at mathematical robustness guarantees. Furthermore, we will extend a new variant of stochastic gradient descent (multiiteration stochastic estimator) recently introduced by PI Tempone for the training and will analyze its convergence properties.

• DFG Programme: Collaborative Research Centres
• Subproject of: SFB 1481: Sparsity and Singular Structures
• Applicant Institution: Rheinisch-Westfälische Technische Hochschule Aachen
• Project Heads: Professor Dr. Sebastian Krumscheid; Professor Dr. Holger Rauhut; Professor Dr.-Ing. Raul Tempone, Ph.D.