all AI news
Cognitively Inspired Learning of Incremental Drifting Concepts. (arXiv:2110.04662v2 [cs.LG] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Humans continually expand their learned knowledge to new domains and learn
new concepts without any interference with past learned experiences. In
contrast, machine learning models perform poorly in a continual learning
setting, where input data distribution changes over time. Inspired by the
nervous system learning mechanisms, we develop a computational model that
enables a deep neural network to learn new concepts and expand its learned
knowledge to new domains incrementally in a continual learning setting. We rely
on the Parallel …
arxiv computational continual data deep neural network distributed distribution embedding humans incremental knowledge learn machine machine learning machine learning models network neural network processing theory