Zobrazeno 1 - 10
of 1 438
pro vyhledávání: '"Naresh, R."'
Autor:
Dbouk, Hassan, Shanbhag, Naresh R.
Randomized ensemble classifiers (RECs), where one classifier is randomly selected during inference, have emerged as an attractive alternative to traditional ensembling methods for realizing adversarially robust classifiers with limited compute requir
Externí odkaz:
http://arxiv.org/abs/2302.01375
Publikováno v:
Advances in Electrical and Computer Engineering, Vol 15, Iss 2, Pp 23-34 (2015)
This paper presents the application of hybrid opposition based disruption operator in gravitational search algorithm (DOGSA) to solve automatic generation control (AGC) problem of four area hydro-thermal-gas interconnected power system. The propose
Externí odkaz:
https://doaj.org/article/8436e4392d87486a836f317023fdeb08
Autor:
Dbouk, Hassan, Shanbhag, Naresh R.
Despite the tremendous success of deep neural networks across various tasks, their vulnerability to imperceptible adversarial perturbations has hindered their deployment in the real world. Recently, works on randomized ensembles have empirically demo
Externí odkaz:
http://arxiv.org/abs/2206.06737
Publikováno v:
Journal of Family Medicine and Primary Care, Vol 13, Iss 3, Pp 890-895 (2024)
Background: Older patients admitted to hospitals have a greater impact on the healthcare system as the population ages. The relationship between the recovery of functional impairments and frailty status in geriatric care units is still not clear. Sim
Externí odkaz:
https://doaj.org/article/7b8031f844b44f26bce7acada7c4ad60
Autor:
Saion K. Roy, Naresh R. Shanbhag
Publikováno v:
IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, Vol 10, Pp 22-30 (2024)
Resistive in-memory computing (IMC) architectures currently lag behind SRAM IMCs and digital accelerators in both energy efficiency and compute density due to their low compute accuracy. This article proposes the use of signal-to-noise-plus-distortio
Externí odkaz:
https://doaj.org/article/28107b97e2f8428e821dcc1d60abbe85
Autor:
Nair, Keerthana R., Ashok, Hridya, Prabhu, Ram Naresh R., Das, Amrutha, Yuvan Shankar, N., Kandasamy, Elngo, Murugadass, K.
Publikováno v:
In Journal of Molecular Liquids 15 July 2024 406
Autor:
Dbouk, Hassan, Shanbhag, Naresh R.
Despite their tremendous successes, convolutional neural networks (CNNs) incur high computational/storage costs and are vulnerable to adversarial perturbations. Recent works on robust model compression address these challenges by combining model comp
Externí odkaz:
http://arxiv.org/abs/2110.14871
Publikováno v:
Journal of Family Medicine & Primary Care. Mar2024, Vol. 13 Issue 3, p890-895. 6p.
Classical adversarial training (AT) frameworks are designed to achieve high adversarial accuracy against a single attack type, typically $\ell_\infty$ norm-bounded perturbations. Recent extensions in AT have focused on defending against the union of
Externí odkaz:
http://arxiv.org/abs/2105.14710
Autor:
Sakthipriya, S., Naresh, R.
Publikováno v:
In Engineering Applications of Artificial Intelligence April 2024 130