Using CODEQ to Train Feed-forward Neural Networks

TL;DR

This paper introduces CODEQ, a novel hybrid meta-heuristic algorithm, for training feed-forward neural networks, demonstrating competitive performance against established methods like particle swarm optimization and differential evolution.

Contribution

The paper presents the first application of CODEQ to train neural networks, combining chaotic search, opposition-based learning, and quantum mechanics concepts.

Findings

CODEQ outperforms PSO and DE on benchmark datasets

The method achieves high training accuracy

It demonstrates robustness across different problem types

Abstract

CODEQ is a new, population-based meta-heuristic algorithm that is a hybrid of concepts from chaotic search, opposition-based learning, differential evolution and quantum mechanics. CODEQ has successfully been used to solve different types of problems (e.g. constrained, integer-programming, engineering) with excellent results. In this paper, CODEQ is used to train feed-forward neural networks. The proposed method is compared with particle swarm optimization and differential evolution algorithms on three data sets with encouraging results.