Training reliable deep learning models which avoid making overconfident ...
The lack of well-calibrated confidence estimates makes neural networks
i...
We introduce a novel, practically relevant variation of the anomaly dete...
Selective classification is the task of rejecting inputs a model would
p...
Time series modeling techniques based on deep learning have seen many
ad...
We might hope that when faced with unexpected inputs, well-designed soft...
Tensors are multidimensional arrays of numerical values and therefore
ge...