Adaptive Sample Selection for Robust Learning under Label Noise
Accepted in WACV 2023
Projects
Memorization in Neural Networks: Does the Loss Function matter?
We look at the nature of robustness provided by symmetric loss functions against label noise and how they resist memorization in neural networks.
Speech-based detection of ALS and Parkinson’s Disease
Research project, SPIRE Lab, Indian Institute of Science, Bengaluru, India
To be updated.