Neural Architecture Search (NAS) methods autonomously discover high-accuracy neural network architectures, outperforming manually crafted ones. However, The NAS methods require high computational costs due to the high dimension search space and the need to train multiple candidate solutions. This paper introduces LCoDeepNEAT, an instantiation of Lamarckian genetic algorithms, which extends the foundational principles of the CoDeepNEAT framework. LCoDeepNEAT co-evolves CNN architectures and their respective final layer weights. The evaluation process of LCoDeepNEAT entails a single epoch of SGD, followed by the transference of the acquired final layer weights to the genetic representation of the network. In addition, it expedites the process of evolving by imposing restrictions on the architecture search space, specifically targeting architectures comprising just two fully connected layers for classification. Our method yields a notable improvement in the classification accuracy of candidate solutions throughout the evolutionary process, ranging from 2% to 5.6%. This outcome underscores the efficacy and effectiveness of integrating gradient information and evolving the last layer of candidate solutions within LCoDeepNEAT. LCoDeepNEAT is assessed across six standard image classification datasets and benchmarked against eight leading NAS methods. Results demonstrate LCoDeepNEAT's ability to swiftly discover competitive CNN architectures with fewer parameters, conserving computational resources, and achieving superior classification accuracy compared to other approaches.

翻译：神经架构搜索（NAS）方法能够自主发现高精度的神经网络架构，其性能优于人工设计的架构。然而，由于搜索空间维度高且需要训练多个候选解，NAS方法通常需要高昂的计算成本。本文提出了LCoDeepNEAT——一种拉马克式遗传算法的具体实现，该算法扩展了CoDeepNEAT框架的基础原理。LCoDeepNEAT协同进化CNN架构及其对应的最终层权重。其评估过程包括单轮随机梯度下降（SGD）训练，随后将获得的最终层权重转移至网络的遗传表征中。此外，该方法通过限制架构搜索空间来加速进化过程，特别针对仅包含两个全连接层进行分类的架构。我们的方法在进化过程中使候选解的分类准确率显著提升了2%至5.6%。这一结果印证了在LCoDeepNEAT中融合梯度信息并进化候选解最终层的有效性与优越性。我们在六个标准图像分类数据集上评估了LCoDeepNEAT，并与八种主流NAS方法进行了基准测试。结果表明，LCoDeepNEAT能够快速发现参数更少、计算资源消耗更低且分类准确率优于其他方法的竞争性CNN架构。