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 2003.11660cs.LGcs.NEq-bio.NC
收藏

R-FORCE:面向随机循环神经网络的鲁棒学习

R-FORCE: Robust Learning for Random Recurrent Neural Networks

Department of Electrical and Computer Engineering, University of Washington(电气与计算机工程系,华盛顿大学)

Yang Zheng, Eli Shlizerman

AI总结:

针对FORCE学习仅在混沌边缘稳定的局限,本文通过约束Jacobian谱的定制初始化提出R-FORCE,显著提升RRNN目标学习的稳定性与精度。

摘要:

随机循环神经网络(RRNN)是用于对序列数据建模并从中提取特征的最简单循环网络。然而,这种简单性是有代价的;众所周知,当采用基于梯度下降的优化进行训练时,RRNN容易受到梯度消失/梯度爆炸问题的影响。为增强RRNN的鲁棒性,已有研究提出了替代训练方法。具体而言,FORCE学习方法提出了一种递归最小二乘替代方案来训练RRNN,并且已被证明甚至适用于具有挑战性的目标学习任务,即在没有引导输入的情况下让网络生成动态模式。虽然FORCE训练表明解决目标学习是可能的,但它似乎只在网络动力学的特定区间(混沌边缘)有效。因此,我们研究按照一种定制分布初始化RRNN连接性是否能够保证鲁棒的FORCE学习。通过推导四项生成原则,我们能够生成这种分布;这些原则约束网络Jacobian矩阵的谱,使其保持在稳定区域内。这种初始化与FORCE学习相结合,提供了一种鲁棒训练方法,即Robust-FORCE(R-FORCE)。我们在多种目标函数上、针对广泛的网络配置验证了R-FORCE的性能,并与替代方法进行了比较。实验表明,R-FORCE为一大类RRNN促成了显著更稳定、更准确的目标学习。正如我们在对身体运动过程中人体关节时间序列进行建模时所证明的那样,这种稳定性在对多维序列建模时变得至关重要。

英文摘要:

Random Recurrent Neural Networks (RRNN) are the simplest recurrent networks to model and extract features from sequential data. The simplicity however comes with a price; RRNN are known to be susceptible to diminishing/exploding gradient problem when trained with gradient-descent based optimization. To enhance robustness of RRNN, alternative training approaches have been proposed. Specifically, FORCE learning approach proposed a recursive least squares alternative to train RRNN and was shown to be applicable even for the challenging task of target-learning, where the network is tasked with generating dynamic patterns with no guiding input. While FORCE training indicates that solving target-learning is possible, it appears to be effective only in a specific regime of network dynamics (edge-of-chaos). We thereby investigate whether initialization of RRNN connectivity according to a tailored distribution can guarantee robust FORCE learning. We are able to generate such distribution by inference of four generating principles constraining the spectrum of the network Jacobian to remain in stability region. This initialization along with FORCE learning provides a robust training method, i.e., Robust-FORCE (R-FORCE). We validate R-FORCE performance on various target functions for a wide range of network configurations and compare with alternative methods. Our experiments indicate that R-FORCE facilitates significantly more stable and accurate target-learning for a wide class of RRNN. Such stability becomes critical in modeling multi-dimensional sequences as we demonstrate on modeling time-series of human body joints during physical movements.

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。

↑