-
Temperature check: theory and practice for training models with softmax-cross-entropy losses
The softmax function combined with a cross-entropy loss is a principled ...
10/14/2020 ∙ by Atish Agarwala, et al. ∙
10
∙
share
read it
-
Learning the gravitational force law and other analytic functions
Large neural network models have been successful in learning functions o...
05/15/2020 ∙ by Atish Agarwala, et al. ∙
0
∙
share
read it
