Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Kabir, H. M. Dipu"'
Autor:
Kabir, H M Dipu
Multitask learning is a popular approach to training high-performing neural networks with improved generalization. In this paper, we propose a background class to achieve improved generalization at a lower computation compared to multitask learning t
Externí odkaz:
http://arxiv.org/abs/2305.03238
Autor:
Kabir, H M Dipu, Mondal, Subrota Kumar, Khanam, Sadia, Khosravi, Abbas, Rahman, Shafin, Qazani, Mohammad Reza Chalak, Alizadehsani, Roohallah, Asadi, Houshyar, Mohamed, Shady, Nahavandi, Saeid, Acharya, U Rajendra
Publikováno v:
Applied Soft Computing, 2023
Researchers have proposed several approaches for neural network (NN) based uncertainty quantification (UQ). However, most of the approaches are developed considering strong assumptions. Uncertainty quantification algorithms often perform poorly in an
Externí odkaz:
http://arxiv.org/abs/2304.14925
Autor:
Khanam, Sadia, Qazani, Mohammad Reza Chalak, Mondal, Subrota Kumar, Kabir, H M Dipu, Sabyasachi, Abadhan S., Asadi, Houshyar, Kumar, Keshav, Tabarsinezhad, Farzin, Mohamed, Shady, Khorsavi, Abbas, Nahavandi, Saeid
This paper proposes transferred initialization with modified fully connected layers for COVID-19 diagnosis. Convolutional neural networks (CNN) achieved a remarkable result in image classification. However, training a high-performing model is a very
Externí odkaz:
http://arxiv.org/abs/2209.09556
Autor:
Joloudari, Javad Hassannataj, Mojrian, Sanaz, Saadatfar, Hamid, Nodehi, Issa, Fazl, Fatemeh, shirkharkolaie, Sahar Khanjani, Alizadehsani, Roohallah, Kabir, H M Dipu, Tan, Ru-San, Acharya, U Rajendra
With the increasing growth of information through smart devices, increasing the quality level of human life requires various computational paradigms presentation including the Internet of Things, fog, and cloud. Between these three paradigms, the clo
Externí odkaz:
http://arxiv.org/abs/2203.12315
Autor:
Albardi, Feras, Kabir, H M Dipu, Bhuiyan, Md Mahbub Islam, Kebria, Parham M., Khosravi, Abbas, Nahavandi, Saeid
Publikováno v:
2021 IEEE International Conference on Systems, Man, and Cybernetics
This study aims to explore different pre-trained models offered in the Torchvision package which is available in the PyTorch library. And investigate their effectiveness on fine-grained images classification. Transfer Learning is an effective method
Externí odkaz:
http://arxiv.org/abs/2110.07097
Autor:
Kabir, H M Dipu, Abdar, Moloud, Jalali, Seyed Mohammad Jafar, Khosravi, Abbas, Atiya, Amir F, Nahavandi, Saeid, Srinivasan, Dipti
Publikováno v:
IEEE Transactions on Artificial Intelligence, 2023
Deep neural networks (DNNs) have achieved the state of the art performance in numerous fields. However, DNNs need high computation times, and people always expect better performance in a lower computation. Therefore, we study the human somatosensory
Externí odkaz:
http://arxiv.org/abs/2007.03347
Autor:
Kabir, H M Dipu, Khosravi, Abbas, Kavousi-Fard, Abdollah, Nahavandi, Saeid, Srinivasan, Dipti
Publikováno v:
Applied Soft Computing, 2021
The neural network (NN)-based direct uncertainty quantification (UQ) methods have achieved the state of the art performance since the first inauguration, known as the lower-upper-bound estimation (LUBE) method. However, currently-available cost funct
Externí odkaz:
http://arxiv.org/abs/1912.12761
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.