用两人协作的遗传算法，高效训练图像分类神经网络。
Dual-Individual Genetic Algorithm: A Dual-Individual Approach for Efficient Training of Multi-Layer Neural Networks
- 采用领头与跟随者双角色机制，兼顾优化与探索。
- 三层数智网络达99.04%训练准确率，测试准确率80%。
- 无需人工调参，适合追求高效率的模型设计者。
本文提出一种改进的遗传算法，用于二值图像分类任务（如猫与非猫分类）。该方法仅使用两个个体进行交叉：领头者（Leader）负责局部搜索，代表主优解；跟随者（Follower）维持多样性，防止过早收敛。核心贡献包括：(1) 自适应层维度机制，无需手动调整网络结构；(2) 生成两组参数集（各5种配置，共10种），按帕累托支配关系和代价排序；(3) 性能优于梯度方法。实验显示，在[12288, 17, 4, 1]三层数智网络上，训练准确率达99.04%，测试准确率80%（代价0.06）；而对比的梯度法在[12288, 20, 7, 5, 1]四层网络上仅达98%训练准确率、80%测试准确率（代价0.092）。
原文摘要 · Abstract (English)
This paper introduces an enhanced Genetic Algorithm technique, which optimizes neural networks for binary image classification tasks, such as cat vs. non-cat classification. The proposed method employs only two individuals for crossover, represented by two parameter sets: Leader and Follower. The Leader focuses on exploitation, representing the primary optimal solution, while the Follower promotes exploration by preserving diversity and avoiding premature convergence. Leader and Follower are modeled as two phases or roles. The key contributions of this work are threefold: (1) a self-adaptive layer dimension mechanism that eliminates the need for manual tuning of layer architectures; (2) generates two parameter sets, leader and follower parameter sets, with 10 layer architecture configurations (5 for each set), ranked by Pareto dominance and cost post-optimization; and (3) achieved better results compared to gradient-based methods. Experimental results show that the proposed method achieves 99.04% training accuracy and 80% testing accuracy (cost = 0.06) on a three-layer network with architecture [12288, 17, 4, 1], higher performance a gradient-based approach that achieves 98% training accuracy and 80% testing accuracy (cost = 0.092) on a four-layer network with architecture [12288, 20, 7, 5, 1].
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。