Deep evolutionary network structured representation (DENSER) is a novel evolutionary approach for the automatic generation of deep neural networks (DNNs) which combines the principles of genetic algorithms (GAs) with those of dynamic structured grammatical evolution (DSGE). The GA-level encodes the macro structure of evolution, i.e., the layers, learning, and/or data augmentation methods (among others); the DSGE-level specifies the parameters of each GA evolutionary unit and the valid range of the parameters. The use of a grammar makes DENSER a general purpose framework for generating DNNs: one just needs to adapt the grammar to be able to deal with different network and layer types, problems, or even to change the range of the parameters. DENSER is tested on the automatic generation of convolutional neural networks (CNNs) for the CIFAR-10 dataset, with the best performing networks reaching accuracies of up to 95.22%. Furthermore, we take the fittest networks evolved on the CIFAR-10, and apply them to classify MNIST, Fashion-MNIST, SVHN, Rectangles, and CIFAR-100. The results show that the DNNs discovered by DENSER during evolution generalise, are robust, and scale. The most impressive result is the 78.75% classification accuracy on the CIFAR-100 dataset, which, to the best of our knowledge, sets a new state-of-the-art on methods that seek to automatically design CNNs.

中文翻译：

---

DENSER：深度进化网络结构化表示

深度进化网络结构化表示 (DENSER) 是一种自动生成深度神经网络 (DNN) 的新型进化方法，它结合了遗传算法 (GA) 和动态结构化语法进化 (DSGE) 的原理。GA 级编码进化的宏观结构，即层、学习和/或数据增强方法（等等）；DSGE-level 指定了每个 GA 进化单元的参数和参数的有效范围。语法的使用使 DENSER 成为生成 DNN 的通用框架：只需要调整语法即可处理不同的网络和层类型、问题，甚至改变参数的范围。DENSER 在 CIFAR-10 数据集的卷积神经网络 (CNN) 的自动生成上进行了测试，性能最好的网络达到高达 95.22% 的准确率。此外，我们采用在 CIFAR-10 上进化的最适合的网络，并将它们应用于分类 MNIST、Fashion-MNIST、SVHN、矩形和 CIFAR-100。结果表明，DENSER 在进化过程中发现的 DNN 具有通用性、鲁棒性和可扩展性。最令人印象深刻的结果是 CIFAR-100 数据集上 78.75% 的分类准确率，据我们所知，这为寻求自动设计 CNN 的方法设置了新的最新技术水平。