Search Results for author:
Found 9 papers, 3 papers with code
RobustNeuralNetworks.jl: a Package for Machine Learning and Data-Driven Control with Certified Robustness
Neural networks are typically sensitive to small input perturbations, leading to unexpected or brittle behaviour.
Learning over All Stabilizing Nonlinear Controllers for a Partially-Observed Linear System
This paper proposes a nonlinear policy architecture for control of partially-observed linear dynamical systems providing built-in closed-loop stability guarantees.
Contraction-Based Methods for Stable Identification and Robust Machine Learning: a Tutorial
This tutorial paper provides an introduction to recently developed tools for machine learning, especially learning dynamical systems (system identification), with stability and robustness constraints.
Distributed Identification of Contracting and/or Monotone Network Dynamics
This paper proposes methods for identification of large-scale networked systems with guarantees that the resulting model will be contracting -- a strong form of nonlinear stability -- and/or monotone, i. e. order relations between states are preserved.
Recurrent Equilibrium Networks: Flexible Dynamic Models with Guaranteed Stability and Robustness
RENs are otherwise very flexible: they can represent all stable linear systems, all previously-known sets of contracting recurrent neural networks and echo state networks, all deep feedforward neural networks, and all stable Wiener/Hammerstein models, and can approximate all fading-memory and contracting nonlinear systems.
Lipschitz-Bounded Equilibrium Networks
In image classification experiments we show that the Lipschitz bounds are very accurate and improve robustness to adversarial attacks.
Lipschitz Bounded Equilibrium Networks
In image classification experiments we show that the Lipschitz bounds are very accurate and improve robustness to adversarial attacks.
A Convex Parameterization of Robust Recurrent Neural Networks
Recurrent neural networks (RNNs) are a class of nonlinear dynamical systems often used to model sequence-to-sequence maps.
Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainability
Stability of recurrent models is closely linked with trainability, generalizability and in some applications, safety.
