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? Recent work (Greydanus et al. 2019) proposed Hamiltonian Neural Networks (HNNs) which can learn the Hamiltonian of a physical system from data using a neural network.

# Upcoming Events

### Generalized Lagrangian Networks

## Events Archive

### Solving Inverse Problems with Data-driven Priors

I will present a Bayesian machine learning architecture that combines a physically motivated parameterization and an analytic error model for the likelihood with a deep generative model providing a powerful data-driven prior for complex signals.

### Barks, Bubbles and Brownies!

We will have therapy dogs available to help calm you, bubble tea to hydrate you and brownies to assist with that chocolate fix.

RSVP not necessary but first come, first serve for the bubble tea!

### Machine Learning for the Sciences

*Taking place every other Friday. Lunch will be provided.*

### Grad Students: Interested in Data Science?

Center for Statistics and Machine Learning is holding an informal graduate information session about its certificate program.

Lunch will be served!

### Recent Advances in Non-Convex Distributed Optimization and Learning

### Diving into TensorFlow 2.0

Description: Please join us for this 90-minute workshop, taught at an intermediate level. We will briefly introduce TensorFlow 2.0, then dive in to writing a few flavors of neural networks. Attendees will need a laptop and an internet connection.

### Can learning theory resist deep learning?

### Machine Learning for the Sciences

*Taking place every other Friday. Lunch will be provided.*

### Convergence Rates of Stochastic Algorithms in Nonsmooth Nonconvex Optimization

Abstract:

### Exploration by Optimization in Partial Monitoring

**Abstract:**