Neural architecture search (NAS) is a hot topic in the field of AutoML, and has begun to outperform human-designed architectures on many machine learning tasks. Motivated by the natural representation form of neural networks by the Cartesian genetic programming (CGP), we propose an evolutionary approach of NAS based on CGP, called CPGNAS, for CNN architectures solving sentence classification task. To evolve the CNN architectures under the framework of CGP, the existing key operations are identified as the types of function nodes of CGP and the evolutionary operations are designed based on evolutionary strategy (ES). The experimental results show that the searched architecture can reach the accuracy of human-designed architectures. The ablation tests identify the Attention function as the single key function node and the Convolution and Attention as the joint key function nodes. However, the linear transformations along could keep the accuracy of evolved architectures over 70%, which is worth of investigating in the future.

翻译：神经结构搜索(NAS)是自动ML领域的一个热题,并已开始在许多机器学习任务上超越人设计的建筑。受笛卡尔基因编程(CGP)自然呈现的神经网络形式驱动,我们提议以CGP(称为CPGNAS)为基础的NAS渐进方法,用于CNN解决判决分类任务的架构。为了在CGP框架内发展CNN结构,现有的关键操作被确定为CGP的功能节点类型,而进化操作是根据进化战略设计的。实验结果显示,搜索的建筑可以达到人设计的建筑的准确性。缩放测试将注意功能确定为单一关键函数节点,而进化和注意作为联合关键函数节点。然而,线性转换可以保持进化结构的准确度超过70%,这值得在未来进行调查。