paper-with-me

Papers

Continual Learning with Memory Cascades

2021-09-22 · NeurIPS Workshop ICBINB 2021 12 · David Kappel, Franscesco Negri, Christian Tetzlaff

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningPermuted-MNIST

Similar Papers 제목 키워드 기반

Cascade-LSTM: Predicting Information Cascades using Deep Neural Networks

2020-04-26 · Sameera Horawalavithana, John Skvoretz, Adriana Iamnitchi

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

2022-09-23 · Yan-Shuo Liang, Wu-Jun Li

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 Learning

On the Convergence of Nonconvex Continual Learning with Adaptive Learning Rate

2021-09-29 · Sungyeob Han, Yeongmo Kim, Jungwoo Lee

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 Classification

Saliency-Augmented Memory Completion for Continual Learning

2022-12-26 · Guangji Bai, Chen Ling, Yuyang Gao, Liang Zhao

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 Classification

Nonconvex Continual Learning with Episodic Memory

2021-01-01 · Sungyeob Han, Yeongmo Kim, Jungwoo Lee

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