Activation Functions for "A Feedforward Unitary Equivariant Neural Network"

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Ma, Pui-Wai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917844711636992
author Ma, Pui-Wai
author_facet Ma, Pui-Wai
contents In our previous work [Ma and Chan (2023)], we presented a feedforward unitary equivariant neural network. We proposed three distinct activation functions tailored for this network: a softsign function with a small residue, an identity function, and a Leaky ReLU function. While these functions demonstrated the desired equivariance properties, they limited the neural network's architecture. This short paper generalises these activation functions to a single functional form. This functional form represents a broad class of functions, maintains unitary equivariance, and offers greater flexibility for the design of equivariant neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14462
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Activation Functions for "A Feedforward Unitary Equivariant Neural Network"
Ma, Pui-Wai
Machine Learning
Neural and Evolutionary Computing
In our previous work [Ma and Chan (2023)], we presented a feedforward unitary equivariant neural network. We proposed three distinct activation functions tailored for this network: a softsign function with a small residue, an identity function, and a Leaky ReLU function. While these functions demonstrated the desired equivariance properties, they limited the neural network's architecture. This short paper generalises these activation functions to a single functional form. This functional form represents a broad class of functions, maintains unitary equivariance, and offers greater flexibility for the design of equivariant neural networks.
title Activation Functions for "A Feedforward Unitary Equivariant Neural Network"
topic Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2411.14462