Results 81 to 90 of about 25,829 (292)
A Comparative Study on the Performance and Security Evaluation of Spiking Neural Networks
IEEE Access, 2022 The brain-inspired Spiking neural networks (SNN) claim to present advantages for visual classification tasks in terms of energy efficiency and inherent robustness.
Yanjie Li +3 more
doaj +1 more source
On Adversarial Robustness: A Neural Architecture Search perspective [PDF]
, 2021 Adversarial robustness of deep learning models has gained much traction in the last few years. Various attacks and defenses are proposed to improve the adversarial robustness of modern-day deep learning architectures.
Mittal, Gaurav +4 more
core +1 more source
Continual Learning for Multimodal Data Fusion of a Soft Gripper
Advanced Robotics Research, EarlyView.Models trained on a single data modality often struggle to generalize when exposed to a different modality. This work introduces a continual learning algorithm capable of incrementally learning different data modalities by leveraging both class‐incremental and domain‐incremental learning scenarios in an artificial environment where labeled data is ...
Nilay Kushawaha, Egidio Falotico
wiley +1 more source
Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
CoRRAdversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily conservative training.
Maayan Ehrenberg +2 more
openaire +3 more sources
Adversarially Robust Kernel Smoothing
, 2021 We propose a scalable robust learning algorithm combining kernel smoothing and robust optimization. Our method is motivated by the convex analysis perspective of distributionally robust optimization based on probability metrics, such as the Wasserstein distance and the maximum mean discrepancy.
Zhu, Jia-Jie +3 more
openaire +5 more sources
Advanced Robotics Research, EarlyView.This work presents a state‐adaptive Koopman linear quadratic regulator framework for real‐time manipulation of a deformable swab tool in robotic environmental sampling. By combining Koopman linearization, tactile sensing, and centroid‐based force regulation, the system maintains stable contact forces and high coverage across flat and inclined surfaces.
Siavash Mahmoudi +2 more
wiley +1 more source
IEEE AccessAdversarial training is a widely used method to improve the robustness of deep learning models in various applications. Although adversarial training enhances the robustness of the target model, it also suffers from an accuracy versus robustness trade ...
Manzoor Hussain +3 more
doaj +1 more source
Robust Generative Adversarial Network
CoRR, 2020 Generative adversarial networks (GANs) are powerful generative models, but usually suffer from instability and generalization problem which may lead to poor generations. Most existing works focus on stabilizing the training of the discriminator while ignoring the generalization properties.
Shufei Zhang +4 more
openaire +2 more sources
Advanced Robotics Research, EarlyView.This review maps the methods to monitor robots’ health by fusing vibration, sound, control signals, vision, force, and oil information with artificial intelligence. It identifies deep learning, transfer learning, digital twins, and physics‐informed models as key methodological pathways enabling earlier diagnosis, safer human–robot collaboration, and ...
Yuting Qiao +6 more
wiley +1 more source
Avoiding catastrophic overfitting in fast adversarial training with adaptive similarity step size.
PLoS ONEAdversarial training has become a primary method for enhancing the robustness of deep learning models. In recent years, fast adversarial training methods have gained widespread attention due to their lower computational cost.
Jie-Chao Zhao +5 more
doaj +1 more source