Zobrazeno 1 - 10
of 1 908
pro vyhledávání: '"Savitha. A. P"'
Autor:
Ma'sum, Muhammad Anwar, Pratama, Mahardhika, Ramasamy, Savitha, Liu, Lin, Habibullah, Habibullah, Kowalczyk, Ryszard
Federated Class Incremental Learning (FCIL) is a new direction in continual learning (CL) for addressing catastrophic forgetting and non-IID data distribution simultaneously. Existing FCIL methods call for high communication costs and exemplars from
Externí odkaz:
http://arxiv.org/abs/2407.20705
The Maker-Breaker resolving game is a game played on a graph $G$ by Resolver and Spoiler. The players taking turns alternately in which each player selects a not yet played vertex of $G$. The goal of Resolver is to select all the vertices in a resolv
Externí odkaz:
http://arxiv.org/abs/2406.15108
Autor:
Ma'sum, Muhammad Anwar, Pratama, Mahardhika, Savitha, Ramasamy, Liu, Lin, Habibullah, Kowalczyk, Ryszard
A continual learning (CL) model is desired for remote sensing image analysis because of varying camera parameters, spectral ranges, resolutions, etc. There exist some recent initiatives to develop CL techniques in this domain but they still depend on
Externí odkaz:
http://arxiv.org/abs/2406.18574
Autor:
Hu, Junfeng, Liu, Xu, Fan, Zhencheng, Yin, Yifang, Xiang, Shili, Ramasamy, Savitha, Zimmermann, Roger
Spatio-temporal graph neural networks have demonstrated efficacy in capturing complex dependencies for urban computing tasks such as forecasting and kriging. However, their performance is constrained by the reliance on extensive data for training on
Externí odkaz:
http://arxiv.org/abs/2405.12452
Autor:
Weng, Weiwei, Pratama, Mahardhika, Zhang, Jie, Chen, Chen, Yee, Edward Yapp Kien, Savitha, Ramasamy
Artificial neural networks, celebrated for their human-like cognitive learning abilities, often encounter the well-known catastrophic forgetting (CF) problem, where the neural networks lose the proficiency in previously acquired knowledge. Despite nu
Externí odkaz:
http://arxiv.org/abs/2405.07142
Autor:
Qiao, Zhongzheng, Pham, Xuan Huy, Ramasamy, Savitha, Jiang, Xudong, Kayacan, Erdal, Sarabakha, Andriy
In autonomous and mobile robotics, a principal challenge is resilient real-time environmental perception, particularly in situations characterized by unknown and dynamic elements, as exemplified in the context of autonomous drone racing. This study i
Externí odkaz:
http://arxiv.org/abs/2405.01054
Autor:
Murthy, Savitha, Sitaram, Dinkar
This paper addresses the problem of improving speech recognition accuracy with lattice rescoring in low-resource languages where the baseline language model is insufficient for generating inclusive lattices. We minimally augment the baseline language
Externí odkaz:
http://arxiv.org/abs/2403.10937
The integration of learning and reasoning is high on the research agenda in AI. Nevertheless, there is only a little attention to use existing background knowledge for reasoning about partially observed scenes to answer questions about the scene. Yet
Externí odkaz:
http://arxiv.org/abs/2403.03203
Autor:
Qiao, Zhongzheng, Pham, Quang, Cao, Zhen, Le, Hoang H, Suganthan, P. N., Jiang, Xudong, Savitha, Ramasamy
Real-world environments are inherently non-stationary, frequently introducing new classes over time. This is especially common in time series classification, such as the emergence of new disease classification in healthcare or the addition of new act
Externí odkaz:
http://arxiv.org/abs/2402.12035
Autor:
Pham, Quang, Do, Giang, Nguyen, Huy, Nguyen, TrungTin, Liu, Chenghao, Sartipi, Mina, Nguyen, Binh T., Ramasamy, Savitha, Li, Xiaoli, Hoi, Steven, Ho, Nhat
Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width. However, effective training of SMoE has proven to be challenging due to the representation coll
Externí odkaz:
http://arxiv.org/abs/2402.02526