Neural network weights are trained as the state of a port-Hamiltonian ODE whose Hamiltonian is the loss, giving a continuous-time optimizer.
Gradient and hamiltonian dynamics applied to learning in neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.NE 1years
2019 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Port-Hamiltonian Approach to Neural Network Training
Neural network weights are trained as the state of a port-Hamiltonian ODE whose Hamiltonian is the loss, giving a continuous-time optimizer.