Introduction to Physics-informed Neural Networks
<p>Over the last decades, artificial neural networks have been used to solve problems in varied applied domains such as computer vision, natural language processing and many more. Recently, another very promising application has emerged in the scientific machine learning (ML) community: the solution of partial differential equations (PDEs) using artificial neural networks, with an approach normally referred to as <strong>physics-informed neural networks</strong> (PINNs). PINNs have been originally introduced in the seminal work in [1] and today they are not limited anymore to a pure research topic but are gaining traction in industry as well, enough to enter the famous Gartner hype cycle for emerging technologies in 2021.</p>
<p><a href="https://towardsdatascience.com/solving-differential-equations-with-neural-networks-afdcf7b8bcc4"><strong>Website</strong></a></p>