Open access
Jul 2026
Adaptive hyperparameter optimization in artificial neural networks using the bobcat optimization algorithm (BOA)
This study proposes an adaptive hyperparameter optimization framework based on the Bobcat Optimization Algorithm for tuning the learning rate and momentum of an ANN, and demonstrates that BOA-ANN achieves a test accuracy of 98.30%, outperforming Bayesian optimization, the Secretary Algorithm, and Automated Model Compression under identical settings.
Mohammed Majid Abdulrazzaq, Nehad T. A. Ramaha, A. A. Hameed et al.
· PeerJ Computer Science · 0 citations