3 papers
cs.NE2025
Bio-Inspired Adaptive Neurons for Dynamic Weighting in Artificial Neural Networks
Ashhadul Islam, Abdesselam Bouzerdoum, Samir Brahim Belhaouari
Traditional neural networks employ fixed weights during inference, limiting their ability to adapt to changing input conditions, unlike biological neurons that adjust signal streng…
cs.AI2025
Large Language Model Enhanced Particle Swarm Optimization for Hyperparameter Tuning for Deep Learning Models
Saad Hameed, Basheer Qolomany, Samir Brahim Belhaouari +3
Determining the ideal architecture for deep learning models, such as the number of layers and neurons, is a difficult and resource-intensive process that frequently relies on human…
cs.CL2025
Systematic Weight Evaluation for Pruning Large Language Models: Enhancing Performance and Sustainability
Ashhadul Islam, Samir Brahim Belhaouari, Amine Bermak
The exponential growth of large language models (LLMs) like ChatGPT has revolutionized artificial intelligence, offering unprecedented capabilities in natural language processing.…