# Dual-Individual Genetic Algorithm: A Dual-Individual Approach for Efficient Training of Multi-Layer Neural Networks

arXiv: https://arxiv.org/abs/2504.17346 · HTML: https://mlsanity.com/paper/2504.17346/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 40 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Builds on (most cited first, 7 of 7)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Deep Reinforcement Learning: An Overview](https://mlsanity.com/paper/1701.07274/) (2017)
- [Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration](https://mlsanity.com/paper/2202.04628/) (2022)
- [Managing engineering systems with large state and action spaces through deep reinforcement learning](https://mlsanity.com/paper/1811.02052/) (2018)
- [Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization](https://mlsanity.com/paper/1905.04100/) (2019)
- [AdaSAM: Boosting Sharpness-Aware Minimization with Adaptive Learning Rate and Momentum for Training Deep Neural Networks](https://mlsanity.com/paper/2303.00565/) (2023)
- [RL-GA: A Reinforcement Learning-Based Genetic Algorithm for Electromagnetic Detection Satellite Scheduling Problem](https://mlsanity.com/paper/2206.05694/) (2022)

## Abstract (arXiv)

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].