1 code implementation • 2 May 2024 • Patricia Pauli, Dennis Gramlich, Frank Allgöwer
This paper is devoted to the estimation of the Lipschitz constant of neural networks using semidefinite programming.
no code implementations • 18 Mar 2024 • Patricia Pauli, Dennis Gramlich, Fran Allgöwer
For this reason, we explicitly provide a state space representation of the Roesser type for 2-D convolutional layers with $c_\mathrm{in}r_1 + c_\mathrm{out}r_2$ states, where $c_\mathrm{in}$/$c_\mathrm{out}$ is the number of input/output channels of the layer and $r_1$/$r_2$ characterizes the width/length of the convolution kernel.
no code implementations • 25 Jan 2024 • Patricia Pauli, Aaron Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Frank Allgöwer, Bin Hu
However, a direct application of LipSDP to the resultant residual ReLU networks is conservative and even fails in recovering the well-known fact that the MaxMin activation is 1-Lipschitz.
no code implementations • 15 Jan 2024 • Nicolas Chatzikiriakos, Kim P. Wabersich, Felix Berkel, Patricia Pauli, Andrea Iannelli
This combination enables us to obtain a corresponding optimal control law, which can be implemented efficiently on embedded platforms.
1 code implementation • 20 Mar 2023 • Patricia Pauli, Ruigang Wang, Ian R. Manchester, Frank Allgöwer
We establish a layer-wise parameterization for 1D convolutional neural networks (CNNs) with built-in end-to-end robustness guarantees.
no code implementations • 6 Mar 2023 • Dennis Gramlich, Patricia Pauli, Carsten W. Scherer, Frank Allgöwer, Christian Ebenbauer
This paper introduces a novel representation of convolutional Neural Networks (CNNs) in terms of 2-D dynamical systems.
no code implementations • 28 Nov 2022 • Patricia Pauli, Dennis Gramlich, Frank Allgöwer
In this work, we propose a dissipativity-based method for Lipschitz constant estimation of 1D convolutional neural networks (CNNs).
no code implementations • 13 Apr 2022 • Ross Drummond, Stephen R. Duncan, Matthew C. Turner, Patricia Pauli, Frank Allgöwer
There is a growing debate on whether the future of feedback control systems will be dominated by data-driven or model-driven approaches.
1 code implementation • 3 Jan 2022 • Patricia Pauli, Niklas Funcke, Dennis Gramlich, Mohamed Amine Msalmi, Frank Allgöwer
This paper is concerned with the training of neural networks (NNs) under semidefinite constraints, which allows for NN training with robustness and stability guarantees.
1 code implementation • 31 Mar 2021 • Patricia Pauli, Dennis Gramlich, Julian Berberich, Frank Allgöwer
In this paper, we analyze the stability of feedback interconnections of a linear time-invariant system with a neural network nonlinearity in discrete time.
no code implementations • 23 Nov 2020 • Patricia Pauli, Johannes Köhler, Julian Berberich, Anne Koch, Frank Allgöwer
In this paper, we present a method to analyze local and global stability in offset-free setpoint tracking using neural network controllers and we provide ellipsoidal inner approximations of the corresponding region of attraction.
no code implementations • 7 May 2020 • Johannes Köhler, Lukas Schwenkel, Anne Koch, Julian Berberich, Patricia Pauli, Frank Allgöwer
Our theoretical findings support various recent studies by showing that 1) adaptive feedback strategies are required to reliably contain the COVID-19 outbreak, 2) well-designed policies can significantly reduce the number of fatalities compared to simpler ones while keeping the amount of social distancing measures on the same level, and 3) imposing stronger social distancing measures early on is more effective and cheaper in the long run than opening up too soon and restoring stricter measures at a later time.
1 code implementation • 6 May 2020 • Patricia Pauli, Anne Koch, Julian Berberich, Paul Kohler, Frank Allgöwer
More specifically, we design an optimization scheme based on the Alternating Direction Method of Multipliers that minimizes not only the training loss of an NN but also its Lipschitz constant resulting in a semidefinite programming based training procedure that promotes robustness.