Re:Teaching physics to neural networks removes 'chaos blindn...
by samcodes on Wednesday June 24, 2020 @02:38AM
(#23624789)
They model a system which they know to be constrained by a closed-form equation called the Hamiltonian. They (cleverly, IMO) force the network’s predictions to be constrained by the Hamiltonian, by choosing the right output and loss function.
I don’t see a way to generalize this to the procedural rule-based systems you describe, unless they too are governed by a fairly simple continuous function Like the Hamiltonian.
I don’t know if it was “dramatic”, but it made me really happy.
If so, this would be dramatic, no?
If you could teach a translation service 'grammar' and then also leverage the pattern matching, could this be a 'fundamental' new idea in AI application?
Or is this just something specific?