Representation Ensembling for Synergistic Lifelong Learning with Quasilinear Complexity. (arXiv:2004.12908v12 [cs.AI] UPDATED)

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 typical
transfer learning algorithms can improve performance on future tasks, their
performance on prior tasks degrades upon learning new tasks (called
catastrophic forgetting). Many recent approaches for continual or lifelong
learning have …

ai arxiv complexity learning