Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks

07/04/2020
by   Tess E. Smidt, et al.
0

Curie's principle states that "when effects show certain asymmetry, this asymmetry must be found in the causes that gave rise to them". We demonstrate that symmetry equivariant neural networks uphold Curie's principle and this property can be used to uncover symmetry breaking order parameters necessary to make input and output data symmetrically compatible. We prove these properties mathematically and demonstrate them numerically by training a Euclidean symmetry equivariant neural network to learn symmetry breaking input to deform a square into a rectangle.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/28/2010

Symmetries of Symmetry Breaking Constraints

Symmetry is an important feature of many constraint programs. We show th...
research
06/22/2018

Replica Symmetry and Replica Symmetry Breaking for the Traveling Salesperson Problem

We study the energy landscape of the Traveling Salesperson problem (TSP)...
research
06/01/2021

Symmetry-via-Duality: Invariant Neural Network Densities from Parameter-Space Correlators

Parameter-space and function-space provide two different duality frames ...
research
03/17/2018

Replica Symmetry Breaking in Bipartite Spin Glasses and Neural Networks

Some interesting recent advances in the theoretical understanding of neu...
research
02/27/2017

Equivariance Through Parameter-Sharing

We propose to study equivariance in deep neural networks through paramet...
research
07/22/2011

Symmetry Breaking in Neuroevolution: A Technical Report

Artificial Neural Networks (ANN) comprise important symmetry properties,...
research
07/02/2020

Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?

Deep neural networks are typically initialized with random weights, with...

Please sign up or login with your details

Forgot password? Click here to reset