Robust Design
8 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Robust Design
Most implemented papers
Towards Robust Vision Transformer
vtddggg/Robust-Vision-Transformer
•
•
CVPR 2022
By using and combining robust components as building blocks of ViTs, we propose Robust Vision Transformer (RVT), which is a new vision transformer and has superior performance with strong robustness.
Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory
ArashRahnama/RobustLyapunovDNNs
•
•
CVPR 2020
We treat each individual layer of the DNN as a nonlinear dynamical system and use Lyapunov theory to prove stability and robustness locally.
Reinforcement Learning for Low-Thrust Trajectory Design of Interplanetary Missions
LorenzoFederici/RobustTrajectoryDesignbyRL
•
•
This paper investigates the use of Reinforcement Learning for the robust design of low-thrust interplanetary trajectories in presence of severe disturbances, modeled alternatively as Gaussian additive process noise, observation noise, control actuation errors on thrust magnitude and direction, and possibly multiple missed thrust events.
Probabilistic robust linear quadratic regulators with Gaussian processes
Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design.
Exploring Robust Architectures for Deep Artificial Neural Networks
Waasem/RobDanns
•
•
The architectures of deep artificial neural networks (DANNs) are routinely studied to improve their predictive performance.
Local Latin Hypercube Refinement for Multi-objective Design Uncertainty Optimization
Optimizing the reliability and the robustness of a design is important but often unaffordable due to high sample requirements.
RID-Noise: Towards Robust Inverse Design under Noisy Environments
thyrixyang/rid-noise-aaai22
•
•
We also define a sample-wise weight, which can be used in the maximum weighted likelihood estimation of an inverse model based on a cINN.
Inverse deep learning methods and benchmarks for artificial electromagnetic material design
Deep learning (DL) inverse techniques have increased the speed of artificial electromagnetic material (AEM) design and improved the quality of resulting devices.
