Matthews Correlation Coefficient
A statistical measure for evaluating binary classification quality that incorporates true positives, false positives, true negatives, and false negatives. It is considered a more informative indicator of classifier performance than accuracy, particularly on imbalanced datasets.
Timeline (last 90 days)
Across all architecture × dataset combinations examined, the geometric method comprehensively outperforms magnitude pruning and pruning based solely on local Fisher information on both accuracy and Matthews Correlation Coefficient (MCC) metrics.
The Matthews Correlation Coefficient (MCC) takes into account true positives, true negatives, false positives, and false negatives, with a value range of [-1, 1], and is more robust to class imbalance problems than accuracy.
The Matthews Correlation Coefficient (MCC) ranges from -1 to +1, where +1 indicates perfect prediction, 0 indicates random guessing, and -1 indicates completely inverse prediction
All Facts (3)
Across all architecture × dataset combinations examined, the geometric method comprehensively outperforms magnitude pruning and pruning based solely on local Fisher information on both accuracy and Matthews Correlation Coefficient (MCC) metrics.
50%UnverifiedThe Matthews Correlation Coefficient (MCC) takes into account true positives, true negatives, false positives, and false negatives, with a value range of [-1, 1], and is more robust to class imbalance problems than accuracy.
50%UnverifiedThe Matthews Correlation Coefficient (MCC) ranges from -1 to +1, where +1 indicates perfect prediction, 0 indicates random guessing, and -1 indicates completely inverse prediction
50%