no code implementations • 18 Mar 2024 • Jisu Han, Jaemin Na, Wonjun Hwang
Continual learning aims to refine model parameters for new tasks while retaining knowledge from previous tasks.
no code implementations • 9 May 2023 • Jisu Han, Jaemin Na, Wonjun Hwang
We also propose a method to selectively interpolate the weight of the previous model for a balance between stability and plasticity, and we adjust whether to transfer through model confidence to ensure the performance of the previous class and enable exploratory learning.