Random Multimodel Deep Learning Classifier With Political Optimizer

EasyChair Preprint 13082

Abstract

This study proposes a unique hybrid classifier that merges Random Multimodal Deep Learning (RMDL) with the Political Optimizer (PO) algorithm. RMDL is designed to address the challenge of identifying optimal deep learning architectures across diverse data types, while PO leverages insights from political dynamics to enhance optimization processes. By combining RMDL's collective decision-making with PO's adaptive solution framework, the hybrid classifier achieves improved robustness and accuracy. Evaluation using benchmark functions highlights its exceptional convergence speed and exploration capabilities. Real-world applications are demonstrated through efficient resolution of engineering optimization problems. This innovative integration presents a promising avenue for tackling complex classification tasks across various domains

Keyphrases: Ensemble-based methods, Hybrid Classifier, Political optimization, optimization algorithms

@booklet{EasyChair:13082,
  author    = {K Adilakshmi and Rishika Bashetty and Anuradha Kodali and Harika Gummadi and Sravani Kulla and Sruthi Kusangi},
  title     = {Random Multimodel Deep Learning Classifier With Political Optimizer},
  howpublished = {EasyChair Preprint 13082},
  year      = {EasyChair, 2024}}