We propose a novel approach for the challenge of designing less complex yet highly effective convolutional neural networks (CNNs) through the use of cartesian genetic programming (CGP) for neural architecture search (NAS). Our approach combines real-based and block-chained CNNs representations based on CGP for optimization in the continuous domain using multi-objective evolutionary algorithms (MOEAs). Two variants are introduced that differ in the granularity of the search space they consider. The proposed CGP-NASV1 and CGP-NASV2 algorithms were evaluated using the non-dominated sorting genetic algorithm II (NSGA-II) on the CIFAR-10 and CIFAR-100 datasets. The empirical analysis was extended to assess the crossover operator from differential evolution (DE), the multi-objective evolutionary algorithm based on decomposition (MOEA/D) and S metric selection evolutionary multi-objective algorithm (SMS-EMOA) using the same representation. Experimental results demonstrate that our approach is competitive with state-of-the-art proposals in terms of classification performance and model complexity.

翻译：我们提出了一种新方法，通过使用基于笛卡尔遗传编程（CGP）的神经架构搜索（NAS）来设计复杂度更低且高效的卷积神经网络（CNN）。我们的方法结合了基于CGP的实数表示与块链式CNN表示，利用多目标进化算法（MOEAs）在连续域中进行优化。我们引入了两种变体，它们在所考虑的搜索空间的粒度上有所不同。所提出的CGP-NASV1和CGP-NASV2算法采用非支配排序遗传算法II（NSGA-II）在CIFAR-10和CIFAR-100数据集上进行了评估。经验分析进一步扩展到评估来自差分进化（DE）的交叉算子、基于分解的多目标进化算法（MOEA/D）以及S度量选择进化多目标算法（SMS-EMOA），并采用相同的表示形式。实验结果表明，在分类性能和模型复杂度方面，我们的方法可与现有最优方案相竞争。