May 22, 2017

Modeling individual then average vs modeling average (using Deep Neural Network)

"Our belief is that forcing a neural network to model the individual doctors and then averaging at test time should give better generalization than simply training a neural network to model the average of the doctors."
Reference: https://arxiv.org

No comments:

Carlo Cipolla's Laws of Stupidity

    "By creating a graph of Cipolla's two factors, we obtain four groups of people. Helpless people contribute to society but are...