Saved in:
Bibliographic Details
Main Author: Stinis, Panos
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.15299
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910145393459200
author Stinis, Panos
author_facet Stinis, Panos
contents We propose a novel approach which exploits chaos to enhance classification accuracy. Specifically, the available data that need to be classified are treated as vectors that are first lifted into a higher-dimensional space and then used as initial conditions for the evolution of a chaotic dynamical system for a prescribed temporal interval. The evolved state of the dynamical system is then fed to a trainable softmax classifier which outputs the probabilities of the various classes. As proof-of-concept, we use samples of randomly perturbed orthogonal vectors of moderate dimension (2 to 20), with a corresponding number of classes equal to the vector dimension, and show how our approach can both significantly accelerate the training process and improve the classification accuracy compared to a standard softmax classifier which operates on the original vectors, as well as a softmax classifier which only lifts the vectors to a higher-dimensional space without evolving them. We also provide an explanation for the improved performance of the chaos-enhanced classifier and a selection process for the optimal chaotic evolution interval.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15299
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing classification accuracy through chaos
Stinis, Panos
Machine Learning
68T99
We propose a novel approach which exploits chaos to enhance classification accuracy. Specifically, the available data that need to be classified are treated as vectors that are first lifted into a higher-dimensional space and then used as initial conditions for the evolution of a chaotic dynamical system for a prescribed temporal interval. The evolved state of the dynamical system is then fed to a trainable softmax classifier which outputs the probabilities of the various classes. As proof-of-concept, we use samples of randomly perturbed orthogonal vectors of moderate dimension (2 to 20), with a corresponding number of classes equal to the vector dimension, and show how our approach can both significantly accelerate the training process and improve the classification accuracy compared to a standard softmax classifier which operates on the original vectors, as well as a softmax classifier which only lifts the vectors to a higher-dimensional space without evolving them. We also provide an explanation for the improved performance of the chaos-enhanced classifier and a selection process for the optimal chaotic evolution interval.
title Enhancing classification accuracy through chaos
topic Machine Learning
68T99
url https://arxiv.org/abs/2603.15299