In many engineering systems, we understand part of the physics but not all of it. There may be an unknown friction term, an unmodeled actuator lag, or a hidden coupling between thermal and electrical subsystems. That’s where Dyad Model Discovery comes in.

Powered by Universal Differential Equations (UDEs), Dyad lets you embed neural networks directly into your physical models, train them on experimental data, and recover interpretable equations from what the network has learned.

In this webinar, you’ll learn how to:

• Insert and train neural components within Dyad models

• Use experimental data to learn unmodeled dynamics

• Apply symbolic regression to extract human-readable equations

See how Dyad bridges physics-based modeling with data-driven learning: maintaining structure, interpretability, and physical consistency while letting your models learn from reality.