Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Diversity Regularization in Deep Ensembles
Changjian Shui, Azadeh Sadat Mozafari, Jonathan Marek, Ihsen Hedhli, Christian Gagné
Feb 12, 2018 (modified: Feb 12, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract:Calibrating the confidence of supervised learning models is important for a variety of contexts where the certainty over predictions should be reliable. However, it as been reported that deep neural network models are often too poorly calibrated for achieving complex tasks requiring reliable uncertainty estimates in their prediction. In this work, we are proposing a strategy for training deep ensembles with a diversity function regularization, which improves the calibration property while maintaining a similar prediction accuracy.