FormalizingtheGeneralization-ForgettingTrade-Off inContinualLearning

Neural Information Processing Systems 

In continual learning (CL), we incrementally adapt a model to learn tasks (defined according to the problem at hand) observed sequentially. CL has two main objectives: maintain long-term memory (remember previous tasks) and navigate new experiences continually (quickly adapt to newtasks).

Similar Docs  Excel Report  more

TitleSimilaritySource
None found