An Empirical Study of Example Forgetting during Deep Neural Network Learning
ICLR, Volume abs/1812.05159, 2019.
Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks. Our goal is to understand whether a related phenomenon occurs when data does not undergo a clear distributional shift. We define a `forgetting eventu0027 to have occurred when an indi...More
PPT (Upload PPT)