マイクロ平均は、一般的に用いられる統計的手法です マルチクラス分類 tasks within the field of 人工知能 and 機械学習. It provides a way to assess the performance of a classification model by considering all classes together, rather than calculating metrics for each class separately. This approach is particularly useful when dealing with 不均衡なデータセット いくつかのクラスが他よりも著しく多くのサンプルを持つ場合に
In micro-averaging, the true positives, false positives, and false negatives are summed across all classes before calculating the overall precision, recall, or F1 score. This means that each instance contributes equally to the final metric, regardless of which class it belongs to. The formula for micro-average precision (P) and recall (R) can be expressed as:
- マイクロ平均精度： P = (真陽性の合計) / (真陽性の合計 + 偽陽性の合計)
- マイクロ平均リコール： R = (真陽性の合計) / (真陽性の合計 + 偽陰性の合計)
Micro-average is particularly advantageous in scenarios where the focus is on overall model performance rather than on individual class performance. This can help in providing a more holistic view of a model’s capabilities, especially in applications such as 画像分類, text categorization, and speech recognition.