Optimizing Connection Weights in Neural Networks Using Hybrid Metaheuristics Algorithms

The learning process of artificial neural networks is an important and complex task in the supervised field. main difficulty training a network fine-tuning best set control parameters terms weight bias. This paper presents new method based on hybrid particle swarm optimization with Multi-Verse Optimization (PMVO) to train feedforward networks. algorithm utilized search better solution space which proves its efficiency reducing problems trapping local minima. performance proposed approach was compared five evolutionary techniques standard momentum backpropagation adaptive rate. comparison benchmarked evaluated using six bio-medical datasets. results comparative study show that PMVO outperformed other methods most datasets can be alternative methods.