281 citations · 819 across the 24 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.LG2021
Memorization in Deep Neural Networks: Does the Loss Function matter?
Deep Patel, P. S. Sastry
Deep Neural Networks, often owing to the overparameterization, are shown to be capable of exactly memorizing even randomly labelled data. Empirical studies have also shown that non…
cs.LG2021★ 6 cited
Adaptive Sample Selection for Robust Learning under Label Noise
Deep Patel, P. S. Sastry
Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such…
cs.LG2021
Learning Gaussian-Bernoulli RBMs using Difference of Convex Functions Optimization
Vidyadhar Upadhya, P S Sastry
The Gaussian-Bernoulli restricted Boltzmann machine (GB-RBM) is a useful generative model that captures meaningful features from the given -dimensional continuous data. The diff…