Henry, Akhila and Sundaravaradhan, Rajan and Nagaraj, Nithin (2025) Simplified neurochaos learning architectures for data classification. Chaos: An Interdisciplinary Journal of Nonlinear Science, 35 (6). pp. 1-16.
![]() |
Text
CHA25-AR-AMP2024-00258.pdf - Published Version Restricted to Registered users only Download (774kB) |
Contribution | Name |
---|
Abstract: | Developing Machine Learning algorithms that can classify datasets with higher accuracy and efficiency is crucial in practical applications. Neurochaos Learning (NL) is a recently proposed algorithm that is inspired by the chaotic firing of neurons in the brain. NL has shown promise in recent times both in terms of classification accuracy and in the number of samples needed for training. In this study, we propose a novel simplification of Neurochaos Learning algorithm by reducing the number of features needed for classification and also reducing the number of hyperparameters needed to be tuned. By using a single feature of the chaotic neural traces (orbit generated by chaotic map) of NL and by using only one hyperparameter, we demonstrate a significant boost in run time of the algorithm while retaining comparable classification accuracy. This single feature could either be the mean of the chaotic neural traces (Tracemean) or the Fluctuation Index (FI) of the chaotic neural traces. The classifier itself could either be a simple cosine similarity (Tracemean ChaosNet, FI ChaosNet) or any of the classical machine learning (ML) classifiers (Tracemean+ML, FI+ML). We compare the performance of these newly proposed simplified NL algorithms on ten publicly available datasets. The proposed simplified NL architectures in this study are able to efficiently classify datasets while taking much less run times. The fact that only a single hyperparmeter needs to be tuned in both architectures (Tracemean ChaosNet and FI ChaosNet) makes them very attractive for practical applications with ease of interpretability |
---|---|
Item Type: | Journal Paper |
Keywords: | Chaotic maps, Chaos theory, Feature extraction, Information theory entropy, Machine learning |
Subjects: | School of Humanities > Consciousness Studies |
Divisions: | Schools > Humanities |
Date Deposited: | 05 Jun 2025 06:32 |
Last Modified: | 05 Jun 2025 06:32 |
Official URL: | https://doi.org/10.1063/5.0263796 |
Related URLs: | |
Funders: | * |
Projects: | * |
DOI: | 10.1063/5.0263796 |
URI: | http://eprints.nias.res.in/id/eprint/2938 |
Actions (login required)
![]() |
View Item |