25 citations · 42 across the 8 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Aligning Multiclass Neural Network Classifier Criterion with Task Performance Metrics
Deyuan Li, Taesoo Daniel Lee, Marynel Vázquez +1
Multiclass neural network classifiers are typically trained using cross-entropy loss but evaluated using metrics derived from the confusion matrix, such as Accuracy, -Score, a…
cs.LG2020
Bridging the Gap: Unifying the Training and Evaluation of Neural Network Binary Classifiers
Nathan Tsoi, Kate Candon, Deyuan Li +2
While neural network binary classifiers are often evaluated on metrics such as Accuracy and -Score, they are commonly trained with a cross-entropy objective. How can this trai…