overfitting
過学習（過剰適合）
Definition 定義
A situation in which a model learns the training data too closely, including its noise, and therefore performs poorly on new data.
Example 例文
To prevent overfitting, we applied dropout and stopped training when the validation loss began to increase.
日本語訳を表示
過学習を防ぐため、ドロップアウトを適用し、検証損失が増加し始めた時点で学習を停止した。
Collocations よく使う組み合わせ
- prevent ~
- reduce ~
- suffer from ~
- risk of ~
「~」の部分に overfitting が入ります。