paper-with-me

홈 › Papers

Episodic memory for continual model learning

2017-12-04 · David G. Nagy, Gergő Orbán

Both the human brain and artificial learning agents operating in real-world or comparably complex environments are faced with the challenge of online model selection. In principle this challenge can be overcome: hierarchical Bayesian inference provides a principled method for model selection and it converges on the same posterior for both off-line (i.e. batch) and online learning. However, maintaining a parameter posterior for each model in parallel has in general an even higher memory cost than storing the entire data set and is consequently clearly unfeasible. Alternatively, maintaining only a limited set of models in memory could limit memory requirements. However, sufficient statistics for one model will usually be insufficient for fitting a different kind of model, meaning that the agent loses information with each model change. We propose that episodic memory can circumvent the challenge of limited memory-capacity online model selection by retaining a selected subset of data points. We design a method to compute the quantities necessary for model selection even when the data is discarded and only statistics of one (or few) learnt models are available. We demonstrate on a simple model that a limited-sized episodic memory buffer, when the content is optimised to retain data with statistics not matching the current representation, can resolve the fundamental challenge of online model selection.

📄 PDF Abstract BibTeX arXiv:1712.01169

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian InferencemodelModel Selection

Similar Papers 제목 키워드 기반

Continual and Multi-task Reinforcement Learning With Shared Episodic Memory

2019-05-07 · Artyom Y. Sorokin, Mikhail S. Burtsev

Episodic memory plays an important role in the behavior of animals and humans. It allows the accumulation of information about current state of the environment in a task-agnostic way. This episodic representation can be …

Continual Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Continual Relation Learning via Episodic Memory Activation and Reconsolidation

2020-07-01 · ACL 2020 6 · Xu Han, Yi Dai, Tianyu Gao, Yankai Lin 외

Continual relation learning aims to continually train a model on new data to learn incessantly emerging novel relations while avoiding catastrophically forgetting old relations. Some pioneering work has proved that stori…

Continual LearningRelation

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

On Tiny Episodic Memories in Continual Learning

2019-02-27 · Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan 외

In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learnin…

Class Incremental LearningContinual LearningTransfer Learning

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