arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.00748cs.LGcs.AImath.DSstat.ML
收藏

深层RNN的短时记忆

Short-term Memory of Deep RNN

University of Pisa(比萨大学)

Claudio Gallicchio

摘要:

深度学习向时态数据处理的扩展正在获得越来越多的研究兴趣。在本文中,我们研究了深度递归神经网络(RNN)在短期记忆能力方面的连续层次中发展的状态动力学特性。我们的研究结果揭示了有趣的见解,揭示了分层作为RNN设计因素的本质。值得注意的是,分层组织的RNN架构中的更高层导致固有地偏向于更长的记忆跨度,甚至在训练循环连接之前。此外,在储备池计算框架的背景下,我们的分析还指出了分层递归组织作为提高水库模型记忆技能的有效方法的好处。

英文摘要:

The extension of deep learning towards temporal data processing is gaining an increasing research interest. In this paper we investigate the properties of state dynamics developed in successive levels of deep recurrent neural networks (RNNs) in terms of short-term memory abilities. Our results reveal interesting insights that shed light on the nature of layering as a factor of RNN design. Noticeably, higher layers in a hierarchically organized RNN architecture results to be inherently biased towards longer memory spans even prior to training of the recurrent connections. Moreover, in the context of Reservoir Computing framework, our analysis also points out the benefit of a layered recurrent organization as an efficient approach to improve the memory skills of reservoir models.

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。

↑