Enhancing CNN Classification with Lamarckian Memetic Algorithms and Local Search

TL;DR

This paper introduces a novel population-based optimization method with local search for CNN training, outperforming traditional gradient-based techniques in accuracy and efficiency, especially for complex networks.

Contribution

The paper presents a two-stage training approach combining Lamarckian memetic algorithms with local search, offering a new alternative for CNN weight optimization.

Findings

Outperforms ADAM in accuracy and efficiency

Effective for high-complexity CNNs with many parameters

Provides a robust alternative to gradient-based methods

Abstract

Optimization is critical for optimal performance in deep neural networks (DNNs). Traditional gradient-based methods often face challenges like local minima entrapment. This paper explores population-based metaheuristic optimization algorithms for image classification networks. We propose a novel approach integrating a two-stage training technique with population-based optimization algorithms incorporating local search capabilities. Our experiments demonstrate that the proposed method outperforms state-of-the-art gradient-based techniques, such as ADAM, in accuracy and computational efficiency, particularly with high computational complexity and numerous trainable parameters. The results suggest that our approach offers a robust alternative to traditional methods for weight optimization in convolutional neural networks (CNNs). Future work will explore integrating adaptive mechanisms for parameter tuning and applying the proposed method to other types of neural networks and real-time applications.