Generalising via Meta-Examples for Continual Learning in the Wild. (arXiv:2101.12081v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2101.12081

Future deep learning systems call for techniques that can deal with the
evolving nature of temporal data and scarcity of annotations when new problems
occur. As a step towards this goal, we present FUSION (Few-shot UnSupervIsed
cONtinual learning), a learning strategy that enables a neural network to learn
quickly and continually on streams of unlabelled data and unbalanced tasks. The
objective is to maximise the knowledge extracted from the unlabelled data
stream (unsupervised), favor the forward transfer of previously learnt …

arxiv continual examples learning meta