Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Fangzhen Zhao"'
Publikováno v:
Algorithms, Vol 15, Iss 12, p 461 (2022)
Adversarial attacks hamper the functionality and accuracy of deep neural networks (DNNs) by meddling with subtle perturbations to their inputs. In this work, we propose a new mask-based adversarial defense scheme (MAD) for DNNs to mitigate the negati
Externí odkaz:
https://doaj.org/article/d0a4e4450e734fc9956abf0a753c4dd9
Deep neural networks (DNN) can achieve high performance when applied to In-Distribution (ID) data which come from the same distribution as the training set. When presented with anomaly inputs not from the ID, the outputs of a DNN should be regarded a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::42f4f84af98bf8534169c58c91c0f8f7
Publikováno v:
Global Oceans 2020: Singapore – U.S. Gulf Coast.
In this paper, an anti-multipath time synchronization method based on Hyperbolic Frequency Modulation (HFM) signal is proposed. It is common for underwater acoustic multipath channel that the first path is not the strongest one which brings difficult
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::42da37f34cd621a304e24e6b1128ff4b
https://doi.org/10.1109/ieeeconf38699.2020.9388971
https://doi.org/10.1109/ieeeconf38699.2020.9388971