Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Yang Yejiang"'
This paper proposes a neural network hybrid modeling framework for dynamics learning to promote an interpretable, computationally efficient way of dynamics learning and system identification. First, a low-level model will be trained to learn the syst
Externí odkaz:
http://arxiv.org/abs/2411.10240
This paper proposes a transition system abstraction framework for neural network dynamical system models to enhance the model interpretability, with applications to complex dynamical systems such as human behavior learning and verification. To begin
Externí odkaz:
http://arxiv.org/abs/2402.11739
In this paper, we propose a method of repairing compressed Feedforward Neural Networks (FNNs) based on equivalence evaluation of two neural networks. In the repairing framework, a novel neural network equivalence evaluation method is developed to com
Externí odkaz:
http://arxiv.org/abs/2402.11737
In this paper, a computationally efficient data-driven hybrid automaton model is proposed to capture unknown complex dynamical system behaviors using multiple neural networks. The sampled data of the system is divided by valid partitions into groups
Externí odkaz:
http://arxiv.org/abs/2304.13811
Autor:
Yang, Yejiang, Xiang, Weiming
In this paper, a robust optimization framework is developed to train shallow neural networks based on reachability analysis of neural networks. To characterize noises of input data, the input training data is disturbed in the description of interval
Externí odkaz:
http://arxiv.org/abs/2107.12801
Publikováno v:
In IFAC PapersOnLine 2024 58(11):7-12
Publikováno v:
In Neurocomputing 28 December 2023 562
Publikováno v:
In Neural Networks July 2022 151:61-69
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Applied Science and Innovative Research. 6:p45
The combination of virtual simulation technology and innovation and entrepreneurship education can achieve the role of interaction between the environment and the real environment during students’ virtual simulation, which can attract active partic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7915e07fae6840201cff6999cd911366
https://doi.org/10.22158/asir.v6n4p45
https://doi.org/10.22158/asir.v6n4p45