Re:Teaching physics to neural networks removes 'chaos blindn...
by vutekst on Tuesday June 23, 2020 @11:32PM
(#23623725)
Also ML non-expert here. I think this is about a different kind of neuron(your 2nd suggestion). The paper another commenter linked says:
Hamiltonian neural network (HNN) intakes position and momenta {q,p}, outputs the scalar function H, takes its gradient to find its position and momentum rates of change, and minimizes the loss
<latex equation for a modified loss function that differs from traditional NN>
Re:Teaching physics to neural networks removes 'chaos blindn...
by zone411 on Wednesday June 24, 2020 @06:55AM
(#23626467)
I haven't used HNNs in practice but it seems that the main difference from common NNs is that the loss function incorporates gradients. It's not a new type of a neuron.
Hamiltonian neural network (HNN) intakes position and momenta {q,p}, outputs the scalar function H, takes its gradient to find its position and momentum rates of change, and minimizes the loss
<latex equation for a modified loss function that differs from traditional NN>
which enforces Hamilton's equations of motion.
https://journals.aps.org/pre/abstract/10.1103/PhysRevE.101.0...