miscellaneous-5

Robust Design

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in robust-design-5

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find robust-design-5 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Towards Robust Vision Transformer

Hui Xue, Shaokai Ye, Yuan He, Xiaofeng Mao, Gege Qi, Yuefeng Chen, Xiaodan Li, Ranjie Duan•Sun May 16 2021

Robust Vision Transformer (RVT) is proposed, which is a new vision transformer and has superior performance with strong robustness and generalization ability compared with previous ViTs and state-of-the-art CNNs.

234

Content

0

Paper Graph

Inverse deep learning methods and benchmarks for artificial electromagnetic material design

Jordan M. Malof, Yang Deng, Simiao Ren, Omar Khatib, Willie J. Padilla, Ashwin Mahendra•Sat Dec 18 2021

This work compares eight state-of-the-art DIMs on three unique AEM design problems, including two models that are novel to the AEM community, and indicates that D IMs can rapidly produce accurate designs to achieve a custom desired scattering on all three problems.

36 0

Paper Graph

Conditioning by adaptive sampling for robust design

David H. Brookes, Hahnbeom Park, J. Listgarten•Mon Jan 28 2019

This work proposes a new method, Conditioning by Adaptive Sampling, which yields state-of-the-art results on a protein fluorescence problem, as compared to other recently published approaches.

224 0

Paper Graph

Robust Design of Deep Neural Networks Against Adversarial Attacks Based on Lyapunov Theory

Edward Raff, Arash Rahnama, A. Nguyen•Mon Nov 11 2019

This work treats each individual layer of the DNN as a nonlinear system and uses Lyapunov theory to prove stability and robustness locally and globally, and develops empirically tight bounds on the response of the output layer, or any hidden layer, to adversarial perturbations added to the input, or the input of hidden layers.

24 0

Paper Graph

Reinforcement Learning for Low-Thrust Trajectory Design of Interplanetary Missions

A. Zavoli, Lorenzo Federici•Tue Aug 18 2020

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 is investigated.

7 0

Paper Graph

Probabilistic robust linear quadratic regulators with Gaussian processes

Alexander von Rohr, Matthias Neumann-Brosig, Sebastian Trimpe•Sun May 16 2021

A novel controller synthesis for linearized GP dynamics that yields robust controllers with respect to a probabilistic stability margin is presented, based on a recently proposed algorithm for linear quadratic control synthesis and extended by giving probabilism robustness guarantees in the form of credibility bounds for the system’s stability.

9 0

Paper Graph

Exploring robust architectures for deep artificial neural networks

A. Waqas, Hamza Farooq, N. Bouaynaya, Ghulam Rasool•Tue Jun 29 2021

It is shown that robustness performance of DANNs can be quantified before training using graph structural properties such as topological entropy and Olivier-Ricci curvature, with the greatest reliability for complex tasks and large DANN's.

17 0

Paper Graph

Local Latin Hypercube Refinement for Multi-objective Design Uncertainty Optimization

Can Bogoclu, D. Roos, Tamara Nestorovi'c•Wed Aug 18 2021

Proposed local Latin hypercube reﬁnement (LoLHR) strategy is model-agnostic and can be combined with any surrogate model because there is no free lunch but possibly a budget one and achieves on average better results compared to other surrogate based strategies on the tested examples.

16 0

Paper Graph

RID-Noise: Towards Robust Inverse Design under Noisy Environments

De-chuan Zhan, Hao Ma, Jia-Qi Yang, Ke-Bin Fan•Mon Dec 06 2021

This work proposes Robust Inverse Design under Noise (RID-Noise), which can utilize existing data to train a conditional invertible neural network, and estimates the robustness of a design parameter by its predictability, measured by the prediction error of a forward neural network.

4 0

Paper Graph

Adding a benchmark result helps the community track progress.