Search Results for author:
Found 3 papers, 2 papers with code
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
The main challenge is that the agent must not forget previous tasks and also adapt to novel tasks in the stream.
Online Continual Learning with Maximal Interfered Retrieval
Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks.
Clustering-Oriented Representation Learning with Attractive-Repulsive Loss
The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
