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 2010.02860cs.LGcs.NEnlin.CD
收藏

学会学习,学会学习

Learn to Synchronize, Synchronize to Learn

Università della Svizzera Italiana(瑞士意大利语大学);Politecnico di Milano(米兰理工大学);University of Manitoba(曼尼托巴大学);University of Exeter(埃克塞特大学)

Pietro Verzelli, Cesare Alippi, Lorenzo Livi

摘要:

近年来,机器学习社区对旨在调查训练过程和机器学习模型的动态方面的研究的兴趣不断增长。特别感兴趣的递归神经网络,我们有储备池计算(RC)的概念简单,快速训练计划的特点范例。然而,驻地协调员运作所依据的指导原则只得到部分理解。在这项工作中,我们分析了广义同步(GS)训练RC解决一个通用的任务时所发挥的作用。特别是,我们展示了GS如何允许水库正确编码系统生成的输入信号到其动态。我们还讨论了学习是可行的,在这种方法的必要和充分条件。此外,我们探讨了遍历性在这个过程中发挥的作用,展示了它的存在如何使学习结果适用于多个输入轨迹。最后,我们表明,满意度的GS可以衡量的手段,相互假近邻指数,这使得有效的从业者的理论推导。

英文摘要:

In recent years, the machine learning community has seen a continuous growing interest in research aimed at investigating dynamical aspects of both training procedures and machine learning models. Of particular interest among recurrent neural networks we have the Reservoir Computing (RC) paradigm characterized by conceptual simplicity and a fast training scheme. Yet, the guiding principles under which RC operates are only partially understood. In this work, we analyze the role played by Generalized Synchronization (GS) when training a RC to solve a generic task. In particular, we show how GS allows the reservoir to correctly encode the system generating the input signal into its dynamics. We also discuss necessary and sufficient conditions for the learning to be feasible in this approach. Moreover, we explore the role that ergodicity plays in this process, showing how its presence allows the learning outcome to apply to multiple input trajectories. Finally, we show that satisfaction of the GS can be measured by means of the Mutual False Nearest Neighbors index, which makes effective to practitioners theoretical derivations.

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。

↑