Saved in:
Bibliographic Details
Main Authors: Ali, Shanookha, Niralda, Nitha, Mathew, Sunil
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.16287
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909798343114752
author Ali, Shanookha
Niralda, Nitha
Mathew, Sunil
author_facet Ali, Shanookha
Niralda, Nitha
Mathew, Sunil
contents The process of pooling vertices involves the creation of a new vertex, which becomes adjacent to all the vertices that were originally adjacent to the endpoints of the vertices being pooled. After this, the endpoints of these vertices and all edges connected to them are removed. In this document, we introduce a formal framework for the concept of fuzzy vertex pooling (FVP) and provide an overview of its key properties with its applications to neural networks. The pooling model demonstrates remarkable efficiency in minimizing loss rapidly while maintaining competitive accuracy, even with fewer hidden layer neurons. However, this advantage diminishes over extended training periods or with larger datasets, where the model's performance tends to degrade. This study highlights the limitations of pooling in later stages of deep learning training, rendering it less effective for prolonged or large-scale applications. Consequently, pooling is recommended as a strategy for early-stage training in advanced deep learning models to leverage its initial efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16287
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Architectural change in neural networks using fuzzy vertex pooling
Ali, Shanookha
Niralda, Nitha
Mathew, Sunil
Machine Learning
05C22, 05C90, 68R10
The process of pooling vertices involves the creation of a new vertex, which becomes adjacent to all the vertices that were originally adjacent to the endpoints of the vertices being pooled. After this, the endpoints of these vertices and all edges connected to them are removed. In this document, we introduce a formal framework for the concept of fuzzy vertex pooling (FVP) and provide an overview of its key properties with its applications to neural networks. The pooling model demonstrates remarkable efficiency in minimizing loss rapidly while maintaining competitive accuracy, even with fewer hidden layer neurons. However, this advantage diminishes over extended training periods or with larger datasets, where the model's performance tends to degrade. This study highlights the limitations of pooling in later stages of deep learning training, rendering it less effective for prolonged or large-scale applications. Consequently, pooling is recommended as a strategy for early-stage training in advanced deep learning models to leverage its initial efficiency.
title Architectural change in neural networks using fuzzy vertex pooling
topic Machine Learning
05C22, 05C90, 68R10
url https://arxiv.org/abs/2509.16287