REVIEW 2 cited by
Task Agnostic Continual Learning Using Online Variational Bayes
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Catastrophic forgetting is the notorious vulnerability of neural networks to the change of the data distribution while learning. This phenomenon has long been considered a major obstacle for allowing the use of learning agents in realistic continual learning settings. A large body of continual learning research assumes that task boundaries are known during training. However, research for scenarios in which task boundaries are unknown during training has been lacking. In this paper we present, for the first time, a method for preventing catastrophic forgetting (BGD) for scenarios with task boundaries that are unknown during training --- task-agnostic continual learning. Code of our algorithm is available at https://github.com/igolan/bgd.
Forward citations
Cited by 2 Pith papers
-
Hierarchically Gated Experts for Efficient Online Continual Learning
GE detects task switches in online continual learning and HGE organizes experts into a tree to select experts faster, with GE competitive on benchmarks but HGE trading accuracy for speed.
-
Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation
Task-Agnostic Policy Distillation pretrains a continual RL agent with curiosity-driven exploration and policy distillation, yielding faster learning and higher scores on five Atari games.
Discussion (0). Continue with ORCID to comment.