Phase-Amplitude Coordinate-Based Neural Networks for Inferring Oscillatory Dynamics

Phase-Amplitude Coordinate-Based Neural Networks for Inferring Oscillatory Dynamics
复制标题

用于推断振荡动力学的基于相位振幅坐标的神经网络

DOI:
10.1007/s00332-023-09994-y
复制
发表时间:
2024
影响因子:
3
通讯作者:
Wilson, Dan
Wilson, Dan
中科院分区:
数学2区
文献类型:
--
作者:
Ahmed, Talha;Wilson, Dan

文献摘要

参考文献

相似文献

在基于降阶相幅坐标的模型降阶框架下,周期非线性系统的动力学可以在超出极限环的情况下得到精确表示。当只有可观测的时间序列数据时,必须使用数据驱动策略来进行模型推理。在这项工作中,我们提出了一种数据驱动的方法,通过考虑降阶模型的傅立叶级数展开并将其重组为已知非线性函数和未知线性函数的组合,可以预测基于相位-幅度坐标的降阶模型的未知周期项。这些线性函数可以被构造为前馈神经网络的权重,并通过对可观测数据的训练来学习获得在幅度坐标的扩展中对任意精度阶有效的降阶模型表示。该方法可以与最近发展的其他降维建模方法结合使用,以产生非常高精度的降阶模型。所提出的策略在考虑突触耦合的神经元群体的动力学的各种例子中得到了说明。
The dynamics of a periodic nonlinear system can be represented accurately beyond the limit cycle in a reduced-order phase-amplitude coordinate-based model reduction framework. When only observable time series data is available, data-driven strategies must be employed for model inference. In this work, we propose a data-driven approach that can predict the unknown, periodic terms of a phase-amplitude coordinate-based reduced-order model by considering their Fourier series expansions and reframing the terms as a composition of a known nonlinear function with an unknown linear function. These linear functions can be structured as weights of a feed-forward neural network and learned to obtain a reduced-order model representation valid to arbitrary orders of accuracy in an expansion of amplitude coordinates by training the network on observable data. The proposed approach can be used in conjunction with other recently developed reduced-order modeling approaches to yield very high accuracy reduced-order models. The proposed strategy is illustrated in a variety of examples that consider the dynamics of a synaptically coupled neuronal population.
DOI: 10.1007/s00285-020-01501-1
发表时间: 2020
影响因子: 1.9
作者:
Wilson, Dan
通讯作者: Wilson, Dan
稳定不动点和周期轨道的库普曼本征函数的一般性质
DOI: 10.1016/j.physd.2021.132959
发表时间: 2020
期刊: IFAC-PapersOnLine
影响因子: --
作者:
Matthew D. Kvalheim;D. Hong;Shai Revzen
通讯作者: Shai Revzen
用于稳定定点动力学的作用角表示的等稳态、等时线和库夫曼谱
DOI: --
发表时间: 2013
期刊:
影响因子: --
作者:
A. Mauroy;I. Mezić;J. Moehlis
通讯作者: J. Moehlis
高精度自适应相位等稳降阶模型的数据驱动推理的直接方法
DOI: 10.1016/j.physd.2023.133675
发表时间: 2023
期刊: Physica D: Nonlinear Phenomena
影响因子: --
作者:
Wilson, Dan
通讯作者: Wilson, Dan
生物系统的相还原和基于相的最优控制:教程
DOI: 10.1007/s00422-018-0780-z
发表时间: 2019
影响因子: 1.9
作者:
Monga, Bharat;Wilson, Dan;Matchen, Tim;Moehlis, Jeff
通讯作者: Moehlis, Jeff