Saved in:
Bibliographic Details
Main Author: Geidarov, Polad
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.23876
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909628215853056
author Geidarov, Polad
author_facet Geidarov, Polad
contents The paper discusses the capabilities of multilayer perceptron neural networks implementing metric recognition methods, for which the values of the weights are calculated analytically by formulas. Comparative experiments in training a neural network with pre-calculated weights and with random initialization of weights on different sizes of the MNIST training dataset are carried out. The results of the experiments show that a multilayer perceptron with pre-calculated weights can be trained much faster and is much more robust to the reduction of the training dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A comparative analysis of a neural network with calculated weights and a neural network with random generation of weights based on the training dataset size
Geidarov, Polad
Machine Learning
Artificial Intelligence
The paper discusses the capabilities of multilayer perceptron neural networks implementing metric recognition methods, for which the values of the weights are calculated analytically by formulas. Comparative experiments in training a neural network with pre-calculated weights and with random initialization of weights on different sizes of the MNIST training dataset are carried out. The results of the experiments show that a multilayer perceptron with pre-calculated weights can be trained much faster and is much more robust to the reduction of the training dataset.
title A comparative analysis of a neural network with calculated weights and a neural network with random generation of weights based on the training dataset size
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.23876