Enhancing classification accuracy through chaos

2026-03-16

AI Summary

This work proposes a novel classification approach that embeds input data into a higher-dimensional space and uses the resulting vector as the initial state of a chaotic dynamical system. After evolving for a fixed duration, the high-dimensional trajectory generated by the system is fed into a trainable Softmax classifier. By integrating chaotic dynamics—characterized by sensitive dependence on initial conditions and complex temporal behavior—into the classification pipeline, the method enhances feature discriminability in a principled manner. To the best of our knowledge, this is the first attempt to leverage chaotic systems explicitly for classification tasks. Experimental results demonstrate that the proposed method consistently achieves significantly higher classification accuracy across multiple datasets compared to standard Softmax classifiers and naive dimensionality expansion strategies, while also accelerating training convergence.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• classification accuracy
• chaos
• softmax classifier
• high-dimensional space
• dynamical system

Innovation

• chaos-enhanced classification
• chaotic dynamical system
• high-dimensional lifting
• softmax classifier
• classification accuracy