I think that is because the undamped spring mass system can be model with *second order homogeneous ordinary differential equation*, y'' + p(x)*y' + q(x)*y = 0. If you model for forced response, E.g. charging response of resistor-inductor-capacitor circuit with 3.3 volts as input, then physics will not be 0. y'' + p(x)*y' + q(x)*y = -3.3.
![Neural ODEs (NODEs) [Physics Informed Machine Learning]](http://i.ytimg.com/vi/nJphsM4obOk/mqdefault.jpg)
![Physics Informed Neural Networks (PINNs) [Physics Informed Machine Learning]](/img/n.gif)
it's great, hardly find teach code video of PINN
Awesome 👌. Thanks for sharing valuable knowledge about the topic.
awesome lecture. Since I am new to PINNs, I just want to know what if we could not have access to the PDEs formulation.....
I wonder if PINNs can solve the three-bodies problem :D
Why there is no collocation loss term in the second example?
Is the Jupyter file of the harmonic oscillator demo available anywhere?
All code shown in the lectures is here: github.com/benmoseley/DLSC-2023
why is the physics loss is 0?
I think that is because the undamped spring mass system can be model with *second order homogeneous ordinary differential equation*, y'' + p(x)*y' + q(x)*y = 0. If you model for forced response, E.g. charging response of resistor-inductor-capacitor circuit with 3.3 volts as input, then physics will not be 0. y'' + p(x)*y' + q(x)*y = -3.3.