2 papers
cs.LG2021
Generation and Analysis of Feature-Dependent Pseudo Noise for Training Deep Neural Networks
Sree Ram Kamabattula, Kumudha Musini, Babak Namazi +2
Training Deep neural networks (DNNs) on noisy labeled datasets is a challenging problem, because learning on mislabeled examples deteriorates the performance of the network. As the…
cs.LG2020
Identifying Training Stop Point with Noisy Labeled Data
Sree Ram Kamabattula, Venkat Devarajan, Babak Namazi +1
Training deep neural networks (DNNs) with noisy labels is a challenging problem due to over-parameterization. DNNs tend to essentially fit on clean samples at a higher rate in the…