Neural ODE — Neural Ordinary Differential Equation

Fact

A model using a neural network to describe change over continuous time.

In Plain Words

Neural ODE is like a volume knob, not a clicky dial. The sound glides up smoothly instead of jumping.

You meet it in data over time and physics models. The path stays smooth, but the computer works harder.

Related Concepts

• Neural Network
• Residual Network
• Automatic Differentiation

Neural-network
A Neural ODE turns layer-to-layer changes into smooth time motion.

ResNet
A Neural ODE is often seen as a ResNet with endless tiny layers.

Autodiff
A Neural ODE needs Autodiff to get gradients through the solving process.