paper-with-me

홈 › Papers

Learning to Remember, Forget and Ignore using Attention Control in Memory

2018-09-28 · T. S. Jayram, Younes Bouhadjar, Ryan L. McAvoy, Tomasz Kornuta, Alexis Asseman, Kamil Rocki, Ahmet S. Ozcan

Typical neural networks with external memory do not effectively separate capacity for episodic and working memory as is required for reasoning in humans. Applying knowledge gained from psychological studies, we designed a new model called Differentiable Working Memory (DWM) in order to specifically emulate human working memory. As it shows the same functional characteristics as working memory, it robustly learns psychology inspired tasks and converges faster than comparable state-of-the-art models. Moreover, the DWM model successfully generalizes to sequences two orders of magnitude longer than the ones used in training. Our in-depth analysis shows that the behavior of DWM is interpretable and that it learns to have fine control over memory, allowing it to retain, ignore or forget information based on its relevance.

📄 PDF Abstract BibTeX arXiv:1809.11087

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language

2026-02-26 · Max S. Bennett, Thomas P. Zollo, Richard Zemel arxiv

Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledge. Continual fine-tuning and in-context learning are costly and brit…

Forgetting in order to Remember Better

2018-12-12

In human memory, forgetting occur rapidly after the remembering and the rate of forgetting slowed down as time went. This is so-called the Ebbinghaus forgetting curve. There are many explanations of how this curve occur …

Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning

2022-03-24 · Pascal Weber, Daniel Wälchli, Mustafa Zeqiri, Petros Koumoutsakos

We present the extension of the Remember and Forget for Experience Replay (ReF-ER) algorithm to Multi-Agent Reinforcement Learning (MARL). ReF-ER was shown to outperform state of the art algorithms for continuous control…

continuous-controlContinuous ControlMulti-agent Reinforcement LearningOpenAI Gym+3

Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping

2021-02-22 · Prakhar Kaushik, Alex Gain, Adam Kortylewski, Alan Yuille

Catastrophic forgetting in neural networks is a significant problem for continual learning. A majority of the current methods replay previous data during training, which violates the constraints of an ideal continual lea…

Continual Learning

Non-parametric Memory for Spatio-Temporal Segmentation of Construction Zones for Self-Driving

2021-01-18 · Min Bai, Shenlong Wang, Kelvin Wong, Ersin Yumer 외

In this paper, we introduce a non-parametric memory representation for spatio-temporal segmentation that captures the local space and time around an autonomous vehicle (AV). Our representation has three important propert…