Zobrazeno 1 - 10
of 686
pro vyhledávání: '"Kumar, Uttam"'
Continual learning (CL) adapt the deep learning scenarios with timely updated datasets. However, existing CL models suffer from the catastrophic forgetting issue, where new knowledge replaces past learning. In this paper, we propose Continual Learnin
Externí odkaz:
http://arxiv.org/abs/2409.17806
Autor:
Jakhmola, Yash, Panja, Madhurima, Mishra, Nitish Kumar, Ghosh, Kripabandhu, Kumar, Uttam, Chakraborty, Tanujit
Spatiotemporal forecasting of traffic flow data represents a typical problem in the field of machine learning, impacting urban traffic management systems. In general, spatiotemporal forecasting problems involve complex interactions, nonlinearities, a
Externí odkaz:
http://arxiv.org/abs/2407.04440
In this article, we deal with the fine boundary regularity, a weighted H\"{o}lder regularity of weak solutions to the problem involving the fractional $(p,q)$-Laplacian denoted by \begin{eqnarray*} \begin{array}{rll} (-\Delta)_{p}^{s} u + (-\Delta)_{
Externí odkaz:
http://arxiv.org/abs/2406.07995
Continual learning (CL) models are designed to learn new tasks arriving sequentially without re-training the network. However, real-world ML applications have very limited label information and these models suffer from catastrophic forgetting. To add
Externí odkaz:
http://arxiv.org/abs/2405.14623
Publikováno v:
Scientific Reports, 2023, Vol. 13
The rapid urbanization trend in most developing countries including India is creating a plethora of civic concerns such as loss of green space, degradation of environmental health, clean water availability, air pollution, traffic congestion leading t
Externí odkaz:
http://arxiv.org/abs/2306.05951
We consider a semipositone problem involving the fractional $p$ Laplace operator of the form \begin{equation*} \begin{aligned} (-\Delta)_p^s u &=\mu( u^{r}-1) \text{ in } \Omega,\\ u &>0 \text{ in }\Omega,\\ u &=0 \text{ on }\Omega^{c}, \end{aligned}
Externí odkaz:
http://arxiv.org/abs/2304.10887
Autor:
Panja, Madhurima, Chakraborty, Tanujit, Nadim, Sk Shahid, Ghosh, Indrajit, Kumar, Uttam, Liu, Nan
Dengue fever is a virulent disease spreading over 100 tropical and subtropical countries in Africa, the Americas, and Asia. This arboviral disease affects around 400 million people globally, severely distressing the healthcare systems. The unavailabi
Externí odkaz:
http://arxiv.org/abs/2212.08323
Publikováno v:
Neural Networks. 2023
Infectious diseases remain among the top contributors to human illness and death worldwide, among which many diseases produce epidemic waves of infection. The unavailability of specific drugs and ready-to-use vaccines to prevent most of these epidemi
Externí odkaz:
http://arxiv.org/abs/2206.10696
Publikováno v:
International Conference on Neural Information Processing 2023
Forecasting time series data is a critical area of research with applications spanning from stock prices to early epidemic prediction. While numerous statistical and machine learning methods have been proposed, real-life prediction problems often req
Externí odkaz:
http://arxiv.org/abs/2204.09640
Autor:
Mihindukulasooriya, Nandana, Dubey, Mohnish, Gliozzo, Alfio, Lehmann, Jens, Ngomo, Axel-Cyrille Ngonga, Usbeck, Ricardo, Rossiello, Gaetano, Kumar, Uttam
Each year the International Semantic Web Conference organizes a set of Semantic Web Challenges to establish competitions that will advance state-of-the-art solutions in some problem domains. The Semantic Answer Type and Relation Prediction Task (SMAR
Externí odkaz:
http://arxiv.org/abs/2112.07606