Progress & Compress : A scalable framework for continual learning

2018

Citations in the corpus

• Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent (2020, neutral): “…growing architectures which keep the past knowledge fixed and store new knowledge in new components, such as new nodes, layers ... (Lee et al. 2018, Schwarz et al. 2018) The idea behind regularization methods is to regularize the objective in order to preserve the knowledge acquired from the…”