둔비의 공부공간

Unlearning이라는 새롭게 접한 분야의 논문이다. AAAI 2023에 Accepted 됐다. https://arxiv.org/abs/2205.08096 https://github.com/vikram2000b/bad-teaching-unlearning GitHub - vikram2000b/bad-teaching-unlearning: Official repo of the paper Can Bad Teaching Induce Forgetting? Unlearning in Deep Official repo of the paper Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher accepte..

Takashi Ishida. (Tokyo Univ) https://arxiv.org/abs/2002.08709 Do We Need Zero Training Loss After Achieving Zero Training Error? Overparameterized deep networks have the capacity to memorize training data with zero \emph{training error}. Even after memorization, the \emph{training loss} continues to approach zero, making the model overconfident and the test performance degraded. Sin arxiv.org ht..