Representation Ensembling for Synergistic Lifelong Learning with Quasilinear Complexity

Jayanta Dey, Joshua Vogelstein, Hayden Helm, Will Levine, Ronak Mehta, Ali Geisa, Haoyin Xu, Gido van de Ven, Emily Chang, Chenyu Gao, Weiwei Yang, Bryan Tower, Jonathan Larson, Christopher White, Carey Priebe

Published: 20 Jan 2022, Last Modified: 28 Mar 2026CrossrefEveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: In biological learning, data are used to improve performance not only on the current task, but also on previously encountered, and as yet unencountered tasks. In contrast, classical machine learning starts from a blank slate, or tabula rasa, using data only for the single task at hand. While typi...
Loading