Geometric Prediction: Moving Beyond Scalars

06/25/2020
by   Raphael J. L. Townshend, et al.
0

Many quantities we are interested in predicting are geometric tensors; we refer to this class of problems as geometric prediction. Attempts to perform geometric prediction in real-world scenarios have been limited to approximating them through scalar predictions, leading to losses in data efficiency. In this work, we demonstrate that equivariant networks have the capability to predict real-world geometric tensors without the need for such approximations. We show the applicability of this method to the prediction of force fields and then propose a novel formulation of an important task, biomolecular structure refinement, as a geometric prediction problem, improving state-of-the-art structural candidates. In both settings, we find that our equivariant network is able to generalize to unseen systems, despite having been trained on small sets of examples. This novel and data-efficient ability to predict real-world geometric tensors opens the door to addressing many problems through the lens of geometric prediction, in areas such as 3D vision, robotics, and molecular and structural biology.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/08/2020

On the geometry of geometric rank

We make a geometric study of the Geometric Rank of tensors recently intr...
research
01/10/2022

Geometric Rank and Linear Determinantal Varieties

There are close relations between tripartite tensors with bounded geomet...
research
03/25/2022

Neural Network Layers for Prediction of Positive Definite Elastic Stiffness Tensors

Machine learning models can be used to predict physical quantities like ...
research
03/17/2023

Geometric Deep Learning for Molecular Crystal Structure Prediction

We develop and test new machine learning strategies for accelerating mol...
research
05/26/2020

DeepRetinotopy: Predicting the Functional Organization of Human Visual Cortex from Structural MRI Data using Geometric Deep Learning

Whether it be in a man-made machine or a biological system, form and fun...
research
01/30/2020

Learn to Predict Sets Using Feed-Forward Neural Networks

This paper addresses the task of set prediction using deep feed-forward ...
research
03/29/2016

The Conditional Lucas & Kanade Algorithm

The Lucas & Kanade (LK) algorithm is the method of choice for efficient ...

Please sign up or login with your details

Forgot password? Click here to reset