arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1809.11087cs.LGcs.NEstat.ML
收藏

学习记忆,忘记和忽略使用注意力控制记忆

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

IBM Research AI(IBM研究院人工智能部门);Almaden Research Center(阿尔马登研究中心)

T. S. Jayram, Younes Bouhadjar, Ryan L. McAvoy, Tomasz Kornuta, Alexis Asseman, Kamil Rocki, Ahmet S. Ozcan

摘要:

典型的具有外部记忆的神经网络不能有效地分离人类推理所需的情景记忆和工作记忆的容量。运用心理学研究中获得的知识,我们设计了一个新的模型,称为可区分工作记忆(DWM),以专门模仿人类的工作记忆。由于它显示出与工作记忆相同的功能特征,它可以强大地学习心理学启发的任务,并且比同类最先进的模型收敛得更快。此外,DWM模型成功地推广到比训练中使用的序列长两个数量级的序列。我们的深入分析表明,DWM的行为是可解释的,它学会了对记忆进行精细的控制,允许它根据相关性保留,忽略或忘记信息。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑