Jun 13, 2024 · Towards robust neural networks via close-loop control. arXiv preprint arXiv ... Adv-bnn: Improved adversarial defense through robust bayesian neural network.

Jun 18, 2024 · Abstract—This paper introduces a novel method for the stability analysis of positive feedback systems with a class of fully connected feedforward neural ...

6 days ago · This paper proposes a predefined time control method for morphing aircraft based on an adaptive full-feedback recurrent neural network and a universal ...

21 hours ago · This thesis focuses on the integration of robustness and stability guarantees in feedback controllers modeled by deep neural networks (DNNs), also known as ...

Jun 14, 2024 · Our approach leverages inclusion functions for the open-loop system and the neural network controller to embed the closed-loop system into a larger-dimensional ...

Jun 24, 2024 · Assessing Visually-Continuous Corruption Robustness of Neural Networks Relative to Human Performance ... ContrastAlign: Toward Robust BEV Feature Alignment via ...

Jun 18, 2024 · Here we propose a robust binary neural network, based on fully differential capacitive neurons and ReRAM synapses, used in a resistive bridge fashion. We ...

Jun 24, 2024 · Using unitary (instead of general) matrices in artificial neural networks (ANNs) is a promising way to solve the gradient explosion/vanishing problem, as well ...

7 days ago · Several closed loop stimulation protocols are implemented. Stimulation cues are given to the model by introducing a sensory neuron (SN) that targets the TC ...

7 days ago · Consequently, this study underscores the effectiveness of our proposed ML framework in the precise and rapid decoding of defensive behaviors within a closed- ...