Evolving convolutional neural networks through grammatical evolution
Ricardo H. R. Lima, Aurora Pozo · Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2019
The use of Convolutional Neural Networks (CNNs) have proven to be a solid approach often used to solve many Machine Learning problems, such as image classification and natural language processing tasks. The manual design of CNNs is a hard task, due to the high number of configurable parameters and possible configurations. Recent studies around the automatic design of CNNs have shown positive results. In this work, we propose to explore the design of CNN architectures through the use of Grammatical Evolution (GE), where a BNF grammar is used to define the CNN components and structural rules. Experiments were performed using the MNIST and CIFAR-10 datasets. The obtained results show that the presented approach achieved competitive results and maintaining relatively small architectures when compared with similar state-of-the-art approaches.