1 citations · 1 across the 2 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2022★ 1 cited
Efficient Augmentation for Imbalanced Deep Learning
Damien Dablain, Colin Bellinger, Bartosz Krawczyk +1
Deep learning models tend to memorize training data, which hurts their ability to generalize to under-represented classes. We empirically study a convolutional neural network's int…
cs.LG2021
Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learning
Colin Bellinger, Andriy Drozdyuk, Mark Crowley +1
The use of reinforcement learning (RL) in scientific applications, such as materials design and automated chemistry, is increasing. A major challenge, however, lies in fact that me…