用进化算法优化卷积网络，比ADAM更准更快。
Enhancing CNN Classification with Lamarckian Memetic Algorithms and Local Search
- 结合两阶段训练与带局部搜索的群体优化算法
- 在复杂模型上准确率更高，计算效率优于ADAM
- 适合参数多、计算量大的图像分类任务
深度神经网络（DNN）的性能高度依赖优化方法。传统基于梯度的方法常陷入局部极小值。本文探索了用于图像分类网络的群体启发式优化算法。提出一种新方法，将两阶段训练与具备局部搜索能力的群体优化算法相结合。实验表明，该方法在高计算复杂度和大量可训练参数条件下，相比ADAM等先进梯度方法，在准确率和计算效率上均表现更优。结果表明，该方法为卷积神经网络（CNN）权重优化提供了稳健替代方案。未来工作将探索自适应参数调优机制，并将该方法应用于其他类型神经网络及实时场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。