利用神经延迟微分方程学习延迟
Learning the Delay Using Neural Delay Differential Equations
AI总结:
本研究受神经常微分方程启发,提出基于延迟微分方程的连续时间神经网络方法,用伴随灵敏度法直接从数据学习参数与延迟,拓展了需预定义延迟的现有模型,验证了其在基准系统上的参数学习能力。
摘要:
近年来,机器学习与动力系统的交叉领域引发了广泛关注。神经常微分方程(Neural Ordinary Differential Equations, NODEs)是这两个领域的重要交叉方向。本文提出了一种基于延迟微分方程(Delay Differential Equations, DDEs)的连续时间神经网络方法。该模型采用伴随灵敏度法,可直接从数据中学习模型参数与延迟量。本方法受NODEs启发,对此前需预先已知延迟值的神经DDE模型进行了拓展。我们对所提方法开展了灵敏度分析,并验证了其从基准系统中学习DDE参数的能力,最后探讨了未来潜在的研究方向与应用场景。
英文摘要:
The intersection of machine learning and dynamical systems has generated considerable interest recently. Neural Ordinary Differential Equations (NODEs) represent a rich overlap between these fields. In this paper, we develop a continuous time neural network approach based on Delay Differential Equations (DDEs). Our model uses the adjoint sensitivity method to learn the model parameters and delay directly from data. Our approach is inspired by that of NODEs and extends earlier neural DDE models, which have assumed that the value of the delay is known a priori. We perform a sensitivity analysis on our proposed approach and demonstrate its ability to learn DDE parameters from benchmark systems. We conclude our discussion with potential future directions and applications.
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。