Saved in:
Bibliographic Details
Main Author: Alpaydin, Ethem
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.04352
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915327050252288
author Alpaydin, Ethem
author_facet Alpaydin, Ethem
contents We propose a ``half'' layer of hidden units that has some of its weights randomly set and some of them trained. A half unit is composed of two stages: First, it takes a weighted sum of its inputs with fixed random weights, and second, the total activation is multiplied and then translated using two modifiable weights, before the result is passed through a nonlinearity. The number of modifiable weights of each hidden unit is thus two and does not depend on the fan-in. We show how such half units can be used in the first or any later layer in a deep network, possibly following convolutional layers. Our experiments on MNIST and FashionMNIST data sets indicate the promise of half layers, where we can achieve reasonable accuracy with a reduced number of parameters due to the regularizing effect of the randomized connections.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04352
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Half-Layered Neural Networks
Alpaydin, Ethem
Machine Learning
We propose a ``half'' layer of hidden units that has some of its weights randomly set and some of them trained. A half unit is composed of two stages: First, it takes a weighted sum of its inputs with fixed random weights, and second, the total activation is multiplied and then translated using two modifiable weights, before the result is passed through a nonlinearity. The number of modifiable weights of each hidden unit is thus two and does not depend on the fan-in. We show how such half units can be used in the first or any later layer in a deep network, possibly following convolutional layers. Our experiments on MNIST and FashionMNIST data sets indicate the promise of half layers, where we can achieve reasonable accuracy with a reduced number of parameters due to the regularizing effect of the randomized connections.
title Half-Layered Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2506.04352