R. C. Sawhney

R. C. Sawhney

Auto-generated profile, based on publicly available information

R. C. Sawhney

Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE

Research Focus & Metrics

Academic Career Length

37Years (1990-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 1990 in International Journal of Biometeorology
Verified
Journal Article
Closed access
PDF file
RSR. C. Sawhney
R. C. Sawhney
AMA. S. Malhotra
A. S. Malhotra

1 January 1998 in The Japanese Journal of Physiology
Verified
Journal Article
Open access
PDF file
AMA.S. Malhotra
A.S. Malhotra
KPK. Pal
K. Pal
RPR. Prasad
R. Prasad
ABA.C. Bajaj
A.C. Bajaj
RKR. Kumar
R. Kumar
RSR.C. Sawhney
R.C. Sawhney
Circulatory levels of insulin and growth hormone (GH) were estimated in nine tropical euglycemic men in New Delhi and during the first week of every month of stay in Dakshin Gangotri, Antarctica. Prolonged residency in Antarctica did not alter GH levels because mean GH values during Austral summer and Austral winter were not significantly different from the New Delhi values. Compared with GH, the insulin levels during March, April, and June were found to be significantly lower than the New Delhi values. In Antarctica, the insulin levels in March, April, May, June, July, and August were also found to be significantly lower than the December values. This decline in insulin in Antarctica might be important in increasing substrate availability for heat production by facilitating lipolysis and hepatic glucose output.

18 July 2023
Verified
Conference Paper
Open access
PCParth Chhabra
Parth Chhabra
ANAtula Tejaswi Neerkaje
Atula Tejaswi Neerkaje
SAShivam Agarwal
Shivam Agarwal
RSRamit Sawhney
Ramit Sawhney
MTMegh Thakkar
Megh Thakkar
SCSudheer Chava
Sudheer Chava
Mixup is an efficient data augmentation technique, which improves generalization by interpolating random examples. While numerous approaches have been developed for Mixup in the Euclidean and in the hyperbolic space, they do not fully use the intrinsic properties of the examples, i.e., they manually set the geometry (Euclidean or hyperbolic) based on the overall dataset, which may be sub-optimal since each example may require a different geometry. We propose DynaMix, a framework that automatically selects an example-specific geometry and performs Mixup between the different geometries to improve training dynamics and generalization. Through extensive experiments in image and text modalities we show that DynaMix outperforms state-of-the-art methods over six downstream applications. We find that DynaMix is more useful in low-resource and semi-supervised settings likely because it displays a probabilistic view of the geometry.