1 code implementation • 23 May 2024 • Indu Solomon, Aye Phyu Phyu Aung, Uttam Kumar, Senthilnath Jayavelu
To address these issues, we propose an unsupervised CL model with task experts called Unsupervised Task Expert Lifelong Learning (U-TELL) to continually learn the data arriving in a sequence addressing catastrophic forgetting.
1 code implementation • 9 Jun 2023 • Rahisha Thottolil, Uttam Kumar, Tanujit Chakraborty
These synthetic urban universes mimic global urban patterns and evaluating their landscape structures through spatial pattern analysis can aid in comprehending landscape dynamics, thereby enhancing sustainable urban planning.
1 code implementation • 16 Dec 2022 • Madhurima Panja, Tanujit Chakraborty, Sk Shahid Nadim, Indrajit Ghosh, Uttam Kumar, Nan Liu
In comparison with statistical, machine learning, and deep learning methods, our proposed XEWNet performs better in 75% of the cases for short-term and long-term forecasting of dengue incidence.
1 code implementation • 21 Jun 2022 • Madhurima Panja, Tanujit Chakraborty, Uttam Kumar, Nan Liu
Unfortunately, most of these past epidemics exhibit nonlinear and non-stationary characteristics due to their spreading fluctuations based on seasonal-dependent variability and the nature of these epidemics.
1 code implementation • 1 Apr 2022 • Madhurima Panja, Tanujit Chakraborty, Uttam Kumar, Abdenour Hadid
In this study, we introduce the Probabilistic AutoRegressive Neural Networks (PARNN), capable of handling complex time series data exhibiting non-stationarity, nonlinearity, non-seasonality, long-range dependence, and chaotic patterns.
no code implementations • 7 Dec 2021 • Nandana Mihindukulasooriya, Mohnish Dubey, Alfio Gliozzo, Jens Lehmann, Axel-Cyrille Ngonga Ngomo, Ricardo Usbeck, Gaetano Rossiello, Uttam Kumar
The Semantic Answer Type and Relation Prediction Task (SMART) task is one of the ISWC 2021 Semantic Web challenges.
no code implementations • 30 Jan 2021 • Nayna Jain, Karthik Nandakumar, Nalini Ratha, Sharath Pankanti, Uttam Kumar
Using the CKKS scheme available in the open-source HElib library, we show that operational parameters of the chosen FHE scheme such as the degree of the cyclotomic polynomial, depth limitations of the underlying leveled HE scheme, and the computational precision parameters have a major impact on the design of the machine learning model (especially, the choice of the activation function and pooling method).