Timezone: »

 
Poster
Hamiltonian Neural Networks
Samuel Greydanus · Misko Dzamba · Jason Yosinski

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #67

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.

Author Information

Sam Greydanus (Oregon State University)

I am a recent graduate of Dartmouth College, where I majored in physics and dabbled in everything else. I have interned at CERN, Microsoft Azure, and the DARPA Explainable AI Project. I like to use memory-based models to generate sequences and policies. So far, I have used them to approximate the Enigma cipher, generate realistic handwriting, and visualize how reinforcement-learning agents play Atari games. One of my priorities as a scientist is to explain my work clearly and make it easy to replicate.

Misko Dzamba (Freenome)
Jason Yosinski (Uber AI; Recursion)

More from the Same Authors