DARTS Meets Ants: A Hybrid Search Strategy for Optimizing KAN-Based 3D CNNs for Violence Recognition in Video
Buribayev Z. Zhassuzak M. Aouani M. Zhangabay Z. Abdirazak Z. Yerkos A.
October 2025Multidisciplinary Digital Publishing Institute (MDPI)
Applied Sciences (Switzerland)
2025#15Issue 20
The optimization capabilities of Kolmogorov–Arnold Networks (KANs) remain largely unexplored, which has limited their practical use in video anomaly recognition compared to conventional 3D-CNNs. To address this gap, we introduce a novel hybrid optimization framework that combines a Minimax Ant System (MMAS) for hyperparameter selection with a modified DARTS strategy for adaptive tuning of the 3D KAN architecture. Unlike existing approaches, our method simultaneously optimizes both learning dynamics and architectural configurations, enabling KANs to better exploit their expressive power in spatiotemporal feature extraction. Applied to a three-class video dataset, the proposed approach improved model accuracy to 87%, surpassing the performance of a standard 3D-CNN by 6%.
3D CNN , ant colony optimization , Kolmogorov–Arnold Network , neural architecture search , spatiotemporal features , violence detection
Text of the article Перейти на текст статьи
Institute of Information and Computational Technologies, Almaty, 050010, Kazakhstan
Department of Computer Science, Al-Farabi Kazakh National University, Almaty, 050040, Kazakhstan
Institute of Information and Computational Technologies
Department of Computer Science
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026