Zobrazeno 1 - 10
of 2 397
pro vyhledávání: '"P., Deeksha"'
Software technologies are used by programmers with diverse backgrounds. To fulfill programmers' need for information, enthusiasts contribute numerous learning resources that vary in style and content, which act as documentation for the corresponding
Externí odkaz:
http://arxiv.org/abs/2412.09422
Autor:
Zhang, Sai Qian, Li, Ziyun, Guo, Chuan, Mahloujifar, Saeed, Dangwal, Deeksha, Suh, Edward, De Salvo, Barbara, Liu, Chiao
Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main goal is to invert the features of an unidentified target image generated
Externí odkaz:
http://arxiv.org/abs/2412.10448
In recent years, there have been significant advances in efficiently solving $\ell_s$-regression using linear system solvers and $\ell_2$-regression [Adil-Kyng-Peng-Sachdeva, J. ACM'24]. Would efficient $\ell_p$-norm solvers lead to even faster rates
Externí odkaz:
http://arxiv.org/abs/2410.24158
This paper presents a numerical method to solve a time-fractional Burgers equation, achieving order of convergence $(2-\alpha)$ in time, here $\alpha$ represents the order of the time derivative. The fractional derivative is modeled by Caputo-Prabhak
Externí odkaz:
http://arxiv.org/abs/2410.20192
Deep learning methods are at the forefront of automated epileptic seizure detection and onset zone localization using scalp-EEG. However, the performance of deep learning methods rely heavily on the quality of annotated training datasets. Scalp EEG i
Externí odkaz:
http://arxiv.org/abs/2410.19815
As continuous learning based video analytics continue to evolve, the role of efficient edge servers in efficiently managing vast and dynamic datasets is becoming increasingly crucial. Unlike their compute architecture, storage and archival system for
Externí odkaz:
http://arxiv.org/abs/2410.05435
Autor:
Gupta, Pranav, Krishnan, Advith, Nanda, Naman, Eswar, Ananth, Agarwal, Deeksha, Gohil, Pratham, Goel, Pratyush
We present a novel dataset aimed at advancing danger analysis and assessment by addressing the challenge of quantifying danger in video content and identifying how human-like a Large Language Model (LLM) evaluator is for the same. This is achieved by
Externí odkaz:
http://arxiv.org/abs/2410.00477
We propose a randomized multiplicative weight update (MWU) algorithm for $\ell_{\infty}$ regression that runs in $\widetilde{O}\left(n^{2+1/22.5} \text{poly}(1/\epsilon)\right)$ time when $\omega = 2+o(1)$, improving upon the previous best $\widetild
Externí odkaz:
http://arxiv.org/abs/2409.20030
The deployment of Deep Neural Networks in energy-constrained environments, such as Energy Harvesting Wireless Sensor Networks, presents unique challenges, primarily due to the intermittent nature of power availability. To address these challenges, th
Externí odkaz:
http://arxiv.org/abs/2408.13696
Autor:
Tomer, Deeksha, Mandal, Bankim Chandra
We introduce and compare two domain decomposition based numerical methods, namely the Dirichlet-Neumann and Neumann-Neumann Waveform Relaxation methods (DNWR and NNWR respectively), tailored for solving partial differential equations (PDEs) incorpora
Externí odkaz:
http://arxiv.org/abs/2408.11171