Zobrazeno 1 - 10
of 80
pro vyhledávání: '"Cai, Feiyang"'
Autor:
Cai, Feiyang, Zhu, Tianyu, Tzeng, Tzuen-Rong, Duan, Yongping, Liu, Ling, Pilla, Srikanth, Li, Gang, Luo, Feng
Artificial intelligence (AI) has significantly advanced computational chemistry research. However, traditional AI methods often rely on task-specific model designs and training, which constrain both the scalability of model size and generalization ac
Externí odkaz:
http://arxiv.org/abs/2410.21422
Verifying safety of neural network control systems that use images as input is a difficult problem because, from a given system state, there is no known way to mathematically model what images are possible in the real-world. We build on recent work t
Externí odkaz:
http://arxiv.org/abs/2405.18554
Autor:
Wang, Weihan, Chou, Chieh, Sevagamoorthy, Ganesh, Chen, Kevin, Chen, Zheng, Feng, Ziyue, Xia, Youjie, Cai, Feiyang, Xu, Yi, Mordohai, Philippos
We propose an accurate and robust initialization approach for stereo visual-inertial SLAM systems. Unlike the current state-of-the-art method, which heavily relies on the accuracy of a pure visual SLAM system to estimate inertial variables without up
Externí odkaz:
http://arxiv.org/abs/2403.07225
Deep neural networks have demonstrated prominent capacities for image classification tasks in a closed set setting, where the test data come from the same distribution as the training data. However, in a more realistic open set scenario, traditional
Externí odkaz:
http://arxiv.org/abs/2203.08441
Publikováno v:
In Catena November 2024 246
Cyber-physical systems (CPSs) use learning-enabled components (LECs) extensively to cope with various complex tasks under high-uncertainty environments. However, the dataset shifts between the training and testing phase may lead the LECs to become in
Externí odkaz:
http://arxiv.org/abs/2104.06613
Autor:
Gu, Yi, Li, Jie, Gao, Yuting, Chen, Ruoxin, Wu, Chentao, Cai, Feiyang, Wang, Chao, Zhang, Zirui
Neural networks are susceptible to catastrophic forgetting. They fail to preserve previously acquired knowledge when adapting to new tasks. Inspired by human associative memory system, we propose a brain-like approach that imitates the associative le
Externí odkaz:
http://arxiv.org/abs/2011.13553
Learning-enabled components (LECs) are widely used in cyber-physical systems (CPS) since they can handle the uncertainty and variability of the environment and increase the level of autonomy. However, it has been shown that LECs such as deep neural n
Externí odkaz:
http://arxiv.org/abs/2003.10804
Autor:
Cai, Feiyang, Koutsoukos, Xenofon
Cyber-physical systems (CPS) greatly benefit by using machine learning components that can handle the uncertainty and variability of the real-world. Typical components such as deep neural networks, however, introduce new types of hazards that may imp
Externí odkaz:
http://arxiv.org/abs/2001.10494
Autor:
Cai, Feiyang
Silicon photonics has emerged as an effective solution to overcome the wiring limit imposed on electronic device (e.g. transistors) density and performance with continued scaling. In the past few decades, researchers all over the world have invested
Externí odkaz:
http://hdl.handle.net/2429/56429