Search Results for author:
Found 3 papers, 0 papers with code
Hyperparameter Selection in Continual Learning
In continual learning (CL) -- where a learner trains on a stream of data -- standard hyperparameter optimisation (HPO) cannot be applied, as a learner does not have access to all of the data at the same time.
Chunking: Forgetting Matters in Continual Learning even without Changing Tasks
Motivated by an analysis of the linear case, we show that per-chunk weight averaging improves performance in the chunking setting and that this performance transfers to the full CL setting.
Class Conditional Gaussians for Continual Learning
DeepCCG works by updating the posterior of a class conditional Gaussian classifier such that the classifier adapts instantly to representation shift.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
