PINN: Physics Informed Neural Networks

Intro

https://en.wikipedia.org/wiki/Physics-informed_neural_networks

Physics-informed neural networks (PINNs) are a type of universal function approximators that can embed the knowledge of any physical laws that govern a given data-set in the learning process, and can be described by partial differential equations (PDEs).[1] They overcome the low data availability of some biological and engineering systems that makes most state-of-the-art machine learning techniques lack robustness, rendering them ineffective in these scenarios.[1] The prior knowledge of general physical laws acts in the training of neural networks (NNs) as a regularization agent that limits the space of admissible solutions, increasing the correctness of the function approximation. This way, embedding this prior information into a neural network results in enhancing the information content of the available data, facilitating the learning algorithm to capture the right solution and to generalize well even with a low amount of training examples.

==> think of it as a SL DNN version of RL's expert trajectory

====> significantly reduce hypothesis space and reduce training time; enforce a baseline of "correctness" of approximation results

==> how exciting! could be a paradigm for how human and machine can collaborate in the future.

Physics Informed Deep Learning