Loss of plasticity in deep continual learning

Form the foundation of modern machine learning and artificial intelligence. These methods are almost always used in two phases, one in which the weights of the network are updated and one in which the weights are held constant while the network is used or evaluated. This contrasts with natural learning and many applications, which require continual learning. It has been unclear whether or not deep learning methods work in continual learning settings. Here we show that they do not-that standard deep-learning methods gradually lose plasticity in continual-learning settings until they learn no better than a shallow network. We show such loss of plasticity using the classic ImageNet dataset and…

• CI
  Canadian Institute for Advanced Research
• AM
  Alberta Machine Intelligence Institute
• D
  DeepMind
• AD
  Alliance de recherche numérique du Canada
• NS
  Natural Sciences and Engineering Research Council of Canada