Continual Learning with Memory Cascades
Continual learning poses an important challenge to machine learning models. Kirkpatrick et al. introduced a model that combats forgetting during continual learning by using a Bayesian prior to transfer knowledge between task switches. This approach showed promising results but the algorithm was given access to the time points when tasks were switched. Using a model of stochastic learning dynamics we show that this model is very closely related to the previously developed cascade model to combat catastrophic forgetting. This general formulation allows us to use the model also for online learning where no knowledge about task switching times is given to the network. Also it allows us to use deeper hierarchies of Bayesian priors. We evaluate this model on the permuted MNIST task. We demonstrate improved task performance during task switching, but find that online learning is still significantly worse when task switching times are unknown to the network.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningPermuted-MNISTSimilar Papers 제목 키워드 기반
Cascade-LSTM: Predicting Information Cascades using Deep Neural Networks
Predicting the flow of information in dynamic social environments is relevant to many areas of the contemporary society, from disseminating health care messages to meme tracking. While predicting the growth of informatio…
Optimizing Class Distribution in Memory for Multi-Label Online Continual Learning
Online continual learning, especially when task identities and task boundaries are unavailable, is a challenging continual learning setting. One representative kind of methods for online continual learning is replay-base…
Continual LearningOn the Convergence of Nonconvex Continual Learning with Adaptive Learning Rate
One of the objectives of continual learning is to prevent catastrophic forgetting in learning multiple tasks sequentially. The memory based continual learning stores a small subset of the data for previous tasks and appl…
Continual Learningimage-classificationImage ClassificationSaliency-Augmented Memory Completion for Continual Learning
Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of t…
Bilevel OptimizationContinual Learningimage-classificationImage ClassificationNonconvex Continual Learning with Episodic Memory
Continual learning aims to prevent catastrophic forgetting while learning a new task without accessing data of previously learned tasks. The memory for such learning scenarios build a small subset of the data for previo…
Continual Learningimage-classificationImage Classification