Neural networks with Euclidean Symmetry for Learning from Physical Systems

Speaker: Tess Smidt , MIT RLE

Date: Wednesday, October 25, 2023

Time: 2:00 PM to 3:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: 32-D451

Event Type: Seminar

Room Description:

Host: Polina Golland, MIT CSAIL

Contact: Sheila Sharbetian, 617-324-6747,

Relevant URL:

Speaker URL: None

Speaker Photo:

Reminders to:

Reminder Subject: TALK: Neural networks with Euclidean Symmetry for Learning from Physical Systems

To use machine learning to tackle challenges in the chemical and biological sciences, we need methods built to handle the “datatypes” of physical systems: geometry and the geometric tensors. These are traditionally challenging datatypes to use for machine learning because coordinates and coordinate systems are sensitive to the symmetries of 3D space: 3D
rotations, translations, and inversion.

In this talk, I present a method that I have been developing with my colleagues for the past five years, Euclidean neural networks. These networks preserve Euclidean symmetry by construction, making them incapable of unphysical bias due to a change of coordinates. They eliminate the need for data augmentation -- the 500-fold increase in brute-force training
necessary for a model to learn 3D patterns in arbitrary orientations. This makes them extremely data-efficient; they result in more accurate models and require less training data to do so, which is ideal for modeling from scientific data that is expensive, difficult to acquire, or highly-varied.

I describe how Euclidean neural networks work, demonstrate their effectiveness on a variety of real-world tasks, and introduce new capabilities my colleagues and I are developing with these methods. I also show how to efficiently and flexibly build equivariant models using our
open-source PyTorch package e3nn (

Research Areas:

Impact Areas:

See other events that are part of the Biomedical Imaging and Analysis 2023 - 2024.

Created by Sheila Sharbetian Email at Thursday, October 12, 2023 at 9:20 AM.