LagrangianNeuralNetwork<T>
Models & Types · AiDotNet.PhysicsInformed.ScientificML
Implements Lagrangian Neural Networks (LNN) for learning mechanical systems.
Inheritance: NeuralNetworkBase<T> → LagrangianNeuralNetwork<T>
How It Works
For Beginners: Lagrangian Neural Networks learn physics using the Lagrangian formulation of mechanics.
Lagrangian Mechanics: Alternative to Hamiltonian mechanics, uses the Lagrangian: L(q, q̇) = T - V = Kinetic Energy - Potential Energy
Equations of Motion (Euler-Lagrange): d/dt(∂L/∂q̇) - ∂L/∂q = 0
Where:
- q = generalized coordinates (positions)
- q̇ = generalized velocities
- T = kinetic energy (usually ½m q̇²)
- V = potential energy (depends on q)
Why Lagrangian vs. Hamiltonian?
- Lagrangian: Uses (q, q̇) - position and velocity
- Hamiltonian: Uses (q, p) - position and momentum
- Lagrangian often more intuitive for mechanical systems
- Both give same physics, different formulations
How LNN Works:
- Neural network learns L(q, q̇)
- Compute ∂L/∂q and ∂L/∂q̇ using automatic differentiation
- Apply Euler-Lagrange equation to get acceleration q̈
- Guaranteed to conserve energy and satisfy principle of least action
Applications:
- Robotics (manipulator dynamics)
- Biomechanics (human motion)
- Aerospace (satellite dynamics)
- Any mechanical system
Example
var lnn = new LagrangianNeuralNetwork<float>();
float[] acceleration = lnn.ComputeAcceleration(
new float[] { 1.0f, 0.5f }, new float[] { 0.1f, -0.2f });
Constructors
| Constructor | Summary |
|---|---|
LagrangianNeuralNetwork() |
Creates a default LagrangianNeuralNetwork with a 2D configuration space. |
LagrangianNeuralNetwork(NeuralNetworkArchitecture<T> architecture, int configurationDim, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer, LagrangianNeuralNetworkOptions options) |
Properties
| Property | Summary |
|---|---|
TrainingObjectiveKind TrainingObjectiveKind { get; } |
|
bool SupportsTraining { get; } |
Serializes Lagrangian-specific data. |
Methods
| Method | Summary |
|---|---|
ModelMetadata<T> GetModelMetadata() |
Gets metadata about the Lagrangian network. |
T ComputeLagrangian(Vector<T> q, Vector<T> qDot) |
Computes the Lagrangian L(q, q̇) = T - V. |
Tensor<T> Forward(Tensor<T> input) |
Performs a forward pass through the network. |
Tensor<T> ForwardForTraining(Tensor<T> input) |
|
Vector<T> ComputeAcceleration(Vector<T> q, Vector<T> qDot) |
Computes acceleration using Euler-Lagrange equation. |