150 citations · 488 across the 33 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.AI2017★ 79 cited
Distance-based Confidence Score for Neural Network Classifiers
Amit Mandelbaum, Daphna Weinshall
The reliable measurement of confidence in classifiers' predictions is very important for many applications and is, therefore, an important part of classifier design. Yet, although…
cs.LG2017★ 7 cited
Every Untrue Label is Untrue in its Own Way: Controlling Error Type with the Log Bilinear Loss
Yehezkel S. Resheff, Amit Mandelbaum, Daphna Weinshall
Deep learning has become the method of choice in many application domains of machine learning in recent years, especially for multi-class classification tasks. The most common loss…