Hamiltonian Neural Networks

06/04/2019
by   Sam Greydanus, et al.
13

Even though neural networks enjoy widespread use, they still struggle to learn the basic laws of physics. How might we endow them with better inductive biases? In this paper, we draw inspiration from Hamiltonian mechanics to train models that learn and respect exact conservation laws in an unsupervised manner. We evaluate our models on problems where conservation of energy is important, including the two-body problem and pixel observations of a pendulum. Our model trains faster and generalizes better than a regular neural network. An interesting side effect is that our model is perfectly reversible in time.

READ FULL TEXT
research
02/10/2022

Deconstructing the Inductive Biases of Hamiltonian Neural Networks

Physics-inspired neural networks (NNs), such as Hamiltonian or Lagrangia...
research
08/05/2021

Symplectic integration of learned Hamiltonian systems

Hamiltonian systems are differential equations which describe systems in...
research
10/07/2021

Lagrangian Neural Network with Differentiable Symmetries and Relational Inductive Bias

Realistic models of physical world rely on differentiable symmetries tha...
research
09/22/2020

Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time

From CNNs to attention mechanisms, encoding inductive biases into neural...
research
11/28/2021

Neural Symplectic Integrator with Hamiltonian Inductive Bias for the Gravitational N-body Problem

The gravitational N-body problem, which is fundamentally important in as...
research
06/23/2020

Learning Potentials of Quantum Systems using Deep Neural Networks

Machine Learning has wide applications in a broad range of subjects, inc...
research
03/10/2020

Lagrangian Neural Networks

Accurate models of the world are built upon notions of its underlying sy...

Please sign up or login with your details

Forgot password? Click here to reset