A New Neural Network Architecture Invariant to the Action of Symmetry Subgroups

12/11/2020
by   Piotr Kicki, et al.
0

We propose a computationally efficient G-invariant neural network that approximates functions invariant to the action of a given permutation subgroup G ≤ S_n of the symmetric group on input data. The key element of the proposed network architecture is a new G-invariant transformation module, which produces a G-invariant latent representation of the input data. Theoretical considerations are supported by numerical experiments, which demonstrate the effectiveness and strong generalization properties of the proposed method in comparison to other G-invariant neural networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/18/2020

A Computationally Efficient Neural Network Invariant to the Action of Symmetry Subgroups

We introduce a method to design a computationally efficient G-invariant ...
research
08/01/2023

Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions

Learning distance functions between complex objects, such as the Wassers...
research
05/16/2023

Noise robust neural network architecture

In which we propose neural network architecture (dune neural network) fo...
research
09/11/2023

Neural Discovery of Permutation Subgroups

We consider the problem of discovering subgroup H of permutation group S...
research
12/14/2016

Deep Function Machines: Generalized Neural Networks for Topological Layer Expression

In this paper we propose a generalization of deep neural networks called...
research
02/27/2017

Equivariance Through Parameter-Sharing

We propose to study equivariance in deep neural networks through paramet...
research
02/04/2022

Group invariant machine learning by fundamental domain projections

We approach the well-studied problem of supervised group invariant and e...

Please sign up or login with your details

Forgot password? Click here to reset