Structured neural networks motivated by dynamical systems

Davide Murari

Math Meets Industry - 02/06/2022

\(\texttt{davide.murari@ntnu.no}\)

Motivation

What are neural networks

\( \mathcal{NN}(x) = f_{\theta_k}\circ ... \circ f_{\theta_1}(x)\)

Dynamical systems interpretation

\( \dot{x}(t) = f(t,x(t),\theta(t)) \)

\mathcal{NN}(x) = \Psi_{f_k}^{h_k}\circ ...\circ \Psi_{f_1}^{h_1}(x)

Layers with a prescribed property \(\mathcal{P}\)

Choose \(f\)

with trajectories that satisfy \(\mathcal{P}\)

Choose \(\Psi^{h_i}_{f_i}\)

that preserves \(\mathcal{P}\)

\(i-\)th layer \(x\mapsto \Psi_{f_i}^{h_i}(x)\)

satisfies \(\mathcal{P}\)

Example : Mass preserving networks

Thank you for the attention

Talk Math Meets Industry 2022

By Davide Murari

Talk Math Meets Industry 2022

Slides talk Math Meets Industry, 02-06-2022, Trondheim

  • 138