This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
CISMN: A Chaos-Integrated Synaptic-Memory Network with Multi-Compartment Chaotic Dynamics for Robust Nonlinear Regression
1
Faculty of Architecture and Urbanism, Tabriz Islamic Art University, Tabriz 5164736931, Iran
2
Faculty of Civil Engineering and Geosciences, Delft University of Technology, 2628 CN Delft, The Netherlands
3
Faculty of Design, Tabriz Islamic Art University, Tabriz 5164736931, Iran
*
Authors to whom correspondence should be addressed.
Mathematics 2025, 13(9), 1513; https://doi.org/10.3390/math13091513 (registering DOI)
Submission received: 6 April 2025
/
Revised: 29 April 2025
/
Accepted: 30 April 2025
/
Published: 4 May 2025
Abstract
Modeling complex, non-stationary dynamics remains challenging for deterministic neural networks. We present the Chaos-Integrated Synaptic-Memory Network (CISMN), which embeds controlled chaos across four modules—Chaotic Memory Cells, Chaotic Plasticity Layers, Chaotic Synapse Layers, and a Chaotic Attention Mechanism—supplemented by a logistic-map learning-rate schedule. Rigorous stability analyses (Lyapunov exponents, boundedness proofs) and gradient-preservation guarantees underpin our design. In experiments, CISMN-1 on a synthetic acoustical regression dataset (541 samples, 22 features) achieved R2 = 0.791 and RMSE = 0.059, outpacing physics-informed and attention-augmented baselines. CISMN-4 on the PMLB sonar benchmark (208 samples, 60 bands) attained R2 = 0.424 and RMSE = 0.380, surpassing LSTM, memristive, and reservoir models. Across seven standard regression tasks with 5-fold cross-validation, CISMN led on diabetes (R2 = 0.483 ± 0.073) and excelled in high-dimensional, low-sample regimes. Ablations reveal a scalability–efficiency trade-off: lightweight variants train in < 10 s with > 95% peak accuracy, while deeper configurations yield marginal gains. CISMN sustains gradient norms (~2 300) versus LSTM collapse (<3), and fixed-seed protocols ensure < 1.2% MAE variation. Interpretability remains challenging (feature-attribution entropy ≈ 2.58 bits), motivating future hybrid explanation methods. CISMN recasts chaos as a computational asset for robust, generalizable modeling across scientific, financial, and engineering domains.
Share and Cite
MDPI and ACS Style
Shahbazi, Y.; Mokhtari Kashavar, M.; Ghaffari, A.; Fotouhi, M.; Pedrammehr, S.
CISMN: A Chaos-Integrated Synaptic-Memory Network with Multi-Compartment Chaotic Dynamics for Robust Nonlinear Regression. Mathematics 2025, 13, 1513.
https://doi.org/10.3390/math13091513
AMA Style
Shahbazi Y, Mokhtari Kashavar M, Ghaffari A, Fotouhi M, Pedrammehr S.
CISMN: A Chaos-Integrated Synaptic-Memory Network with Multi-Compartment Chaotic Dynamics for Robust Nonlinear Regression. Mathematics. 2025; 13(9):1513.
https://doi.org/10.3390/math13091513
Chicago/Turabian Style
Shahbazi, Yaser, Mohsen Mokhtari Kashavar, Abbas Ghaffari, Mohammad Fotouhi, and Siamak Pedrammehr.
2025. "CISMN: A Chaos-Integrated Synaptic-Memory Network with Multi-Compartment Chaotic Dynamics for Robust Nonlinear Regression" Mathematics 13, no. 9: 1513.
https://doi.org/10.3390/math13091513
APA Style
Shahbazi, Y., Mokhtari Kashavar, M., Ghaffari, A., Fotouhi, M., & Pedrammehr, S.
(2025). CISMN: A Chaos-Integrated Synaptic-Memory Network with Multi-Compartment Chaotic Dynamics for Robust Nonlinear Regression. Mathematics, 13(9), 1513.
https://doi.org/10.3390/math13091513
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.