Highway-Connection Classifier Networks for Plastic yet Stable Continual LearningDownload PDF

28 Sept 2020 (modified: 05 May 2023)ICLR 2021 Conference Withdrawn SubmissionReaders: Everyone
Abstract: Paper withdrawn.
One-sentence Summary: This paper provides both theoretical findings and empirical evidences to show that highway connections are effective in preventing forgetting for sequential learning over many tasks.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Reviewed Version (pdf): https://openreview.net/references/pdf?id=K06IzZRXpt
5 Replies

Loading