Multi-objective parametric synthesis of loss functions in neural networks with evolutionary algorithms

The loss function is a fundamental aspect of neural network training and by choosing a suitable one, better results can be achieved. In classification problems, the cross-entropy loss function is almost exclusively used. In this paper the loss function represented by Taylor's series which are o...

Full description

Saved in:
Bibliographic Details
Published in:ITM web of conferences 2024, Vol.59, p.4010
Main Authors: Morozov, Eduard, Stanovov, Vladimir
Format: Article
Language:English
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The loss function is a fundamental aspect of neural network training and by choosing a suitable one, better results can be achieved. In classification problems, the cross-entropy loss function is almost exclusively used. In this paper the loss function represented by Taylor's series which are optimized with multi-objective evolutionary algorithm. As results show the new loss function can be better than cross-entropy, however application of multi-objective algorithm does not bring an improvement in comparison with single-objective algorithm.
ISSN:2271-2097
2271-2097
DOI:10.1051/itmconf/20245904010