The duality between particle methods and artificial neural networks.
The duality between particle methods and artificial neural networks.
复制标题
DOI：
10.1038/s41598-020-73329-0
复制
发表时间：
2020-10-01
影响因子：
4.6
通讯作者：
Moulitsas I
中科院分区：
文献类型：
--
作者：
Alexiadis A;Simmons MJH;Stamatopoulos K;Batchelor HK;Moulitsas I
粒子方法背后的算法非常通用，可用于从分子动力学到天体物理学的各种应用。对于连续介质力学应用，“粒子”的概念可以概括为包括固体和液体物质的离散部分。这项研究表明，可以进一步扩展“粒子”的概念，将人工智能中使用的人工神经元包括在内。这产生了一类基于“粒子-神经元对偶”的新型计算方法，该方法结合了计算粒子模拟物理系统的能力和人工神经元从数据中学习的能力。该方法通过肠道的多物理场模型进行了验证，该模型自主学习如何协调其收缩以推动肠腔内容物向前（蠕动）。训练是通过深度强化学习来实现的。粒子-神经元二元性的优点是将粒子方法扩展到仅部分了解底层物理的系统，但我们的观察使我们能够根据奖励函数凭经验描述缺失的特征。在模拟过程中，模型会自动演化，使其响应适应可用的观测结果，同时与系统的已知物理保持一致。
The algorithm behind particle methods is extremely versatile and used in a variety of applications that range from molecular dynamics to astrophysics. For continuum mechanics applications, the concept of ‘particle’ can be generalized to include discrete portions of solid and liquid matter. This study shows that it is possible to further extend the concept of ‘particle’ to include artificial neurons used in Artificial Intelligence. This produces a new class of computational methods based on ‘particle-neuron duals’ that combines the ability of computational particles to model physical systems and the ability of artificial neurons to learn from data. The method is validated with a multiphysics model of the intestine that autonomously learns how to coordinate its contractions to propel the luminal content forward (peristalsis). Training is achieved with Deep Reinforcement Learning. The particle-neuron duality has the advantage of extending particle methods to systems where the underlying physics is only partially known, but we have observations that allow us to empirically describe the missing features in terms of reward function. During the simulation, the model evolves autonomously adapting its response to the available observations, while remaining consistent with the known physics of the system.
登录
查看更多内容
DOI：
10.1088/0965-0393/18/1/015012
发表时间：
2010-01-01
影响因子：
1.8
作者：
Stukowski, Alexander
通讯作者：
Stukowski, Alexander
影响因子：
4.6
作者：
Kamakoti, Ramji;Dabiri, Yaghoub;Kassab, Ghassan S.
通讯作者：
Kassab, Ghassan S.
DOI：
10.1002/nme.5973
发表时间：
2019-02-10
影响因子：
2.9
作者：
Chen, Hailong;Spencer, Benjamin W.
通讯作者：
Spencer, Benjamin W.
影响因子：
19.6
作者：
Guillard, Francois;Golshan, Pouya;Einav, Itai
通讯作者：
Einav, Itai
影响因子：
4.1
作者：
Monaghan, JJ;Huppert, HE;Worster, MG
通讯作者：
Worster, MG