Skip to content

Pre-trained Dynamics EncoDER

Home / Concepts / Pre-trained Dynamics EncoDER

Pre-trained Dynamics EncoDER

Auto-generated stub. Edit this file to add more details.

A generalized encoder designed to map system observations into a latent space where dynamics are more easily captured, pre-trained using a Lyapunov exponent objective.

Why It Matters

PDEDER is the core proposed architecture designed for generalized representation learning to ease subsequent dynamics modeling across different systems.

Evidence

we conduct a generalized Pre-trained Dynamics EncoDER (PDEDER) which can embed the original state observations into a latent space where the dynamics can be captured more easily.

Metadata & Links