Last Updated:2025/12/07
(computing) A problem setup in machine learning, where, at test time, a learner observes samples from classes that were not observed during training and attempts to predict the class that they belong to, typically based on auxiliary information.
音声機能が動作しない場合はこちらをご確認ください
See correct answer
zero-shot learning
Edit Histories(0)
Source Word
zero-shot learning
Noun
uncountable
Japanese Meaning
(機械学習における)学習時に観測されなかったクラスのデータがテスト時に現れ、それに基づき補助情報などを利用して新たなクラスを予測する問題設定または手法。