Search Results for author: Cheol-Ho Han

Found 1 papers, 0 papers with code

Discriminative Variational Autoencoder for Continual Learning with Generative Replay

no code implementations25 Sep 2019 Woo-Young Kang, Cheol-Ho Han, Byoung-Tak Zhang

Generative replay (GR) is a method to alleviate catastrophic forgetting in continual learning (CL) by generating previous task data and learning them together with the data from new tasks.

Continual Learning Permuted-MNIST +2

Cannot find the paper you are looking for? You can Submit a new open access paper.