首页|New Findings from Villanova University in Machine Learning Provides New Insights (Physics-informed Machine Learning for Modeling Multidimensional Dynamics)
New Findings from Villanova University in Machine Learning Provides New Insights (Physics-informed Machine Learning for Modeling Multidimensional Dynamics)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on Ma chine Learning. According to news reporting originating in Villanova, Pennsylvan ia, by NewsRx journalists, research stated, “This study presents a hybrid modeli ng approach that integrates physics and machine learning for modeling multi-dime nsional dynamics of a coupled nonlinear dynamical system. This approach leverage s principles from classical mechanics, such as the Euler-Lagrange and Hamiltonia n formalisms, to facilitate the process of learning from data.” Financial support for this research came from Office of Naval Research. The news reporters obtained a quote from the research from Villanova University, “The hybrid model incorporates single or multiple artificial neural networks wi thin a customized computational graph designed based on the physics of the probl em. The customization minimizes the potential of violating the underlying physic s and maximizes the efficiency of information flow within the model. The capabil ities of this approach are investigated for various multidimensional modeling sc enarios using different configurations of a coupled nonlinear dynamical system. It is demonstrated that, in addition to improving modeling criteria such as accu racy and consistency with physics, this approach provides additional modeling be nefits. The hybrid model implements a physics-based architecture, enabling the d irect alteration of both conservative and non-conservative components of the dyn amics.”
VillanovaPennsylvaniaUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine LearningVil lanova University
NETL
NSTL
