EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Chaos Control in Recurrent Neural Networks Using a Sinusoidal Activation Function via the Periodic Pulse Method

Franci Zara Manantsoa, Hery Zo Randrianandraina, Minoson Sendrahasina Rakotomalala, Modeste Kameni Nematchoua

Research on Intelligent Manufacturing and Assembly · 2025

DOI: 10.25082/rima.2025.01.003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Research on Intelligent Manufacturing and Assembly, 2025. Verfasst von Franci Zara Manantsoa und 3 weiteren Autor:innen. Die Arbeit nennt 12 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Controlling chaos in recurrent neural networks (RNNs) is a crucial challenge in both computational neuroscience and artificial intelligence. Chaotic behavior in these networks can hinder stability and predictability, particularly in systems requiring structured memory and temporal processing. In this study, we apply the periodic pulse method to stabilize the dynamics of chaotic RNNs using a sinusoidal activation function. Two network configurations (2 and 3 neurons) were analyzed using numerical simulations in MATLAB. Our results show that the periodic pulse method effectively suppresses chaotic behavior, as evidenced by a reduction of the largest Lyapunov exponent from 0.317 to -0.042. The system transitions from an unpredictable regime to a stabilized fixed point. This confirms the method’s potential to regulate nonlinear neural dynamics with minimal external perturbations. Future work will focus on extending this approach to larger recurrent networks (LSTMs, reservoir computing models) and comparing its performance with other chaos control strategies such as delayed feedback and chaotic synchronization. This study contributes to the understanding of chaos in neural networks and its potential applications in neuroscience and AI.

Zitieren

APA

Manantsoa, F. Z., Randrianandraina, H. Z., Rakotomalala, M. S., & Nematchoua, M. K. (2025). Chaos Control in Recurrent Neural Networks Using a Sinusoidal Activation Function via the Periodic Pulse Method. Research on Intelligent Manufacturing and Assembly. https://doi.org/10.25082/rima.2025.01.003

Vancouver

Manantsoa FZ, Randrianandraina HZ, Rakotomalala MS, Nematchoua MK. Chaos Control in Recurrent Neural Networks Using a Sinusoidal Activation Function via the Periodic Pulse Method. Research on Intelligent Manufacturing and Assembly. 2025. doi:10.25082/rima.2025.01.003

BibTeX
@article{Manantsoa2025,
  author = {Manantsoa, Franci Zara and Randrianandraina, Hery Zo and Rakotomalala, Minoson Sendrahasina and Nematchoua, Modeste Kameni},
  title = {Chaos Control in Recurrent Neural Networks Using a Sinusoidal Activation Function via the Periodic Pulse Method},
  journal = {Research on Intelligent Manufacturing and Assembly},
  year = {2025},
  doi = {10.25082/rima.2025.01.003}
}
Kostenlos starten →