A Genetic Programming Approach to Designing Convolutional Neural Network Architectures
This addresses the need for expert knowledge in CNN design, though it is incremental as it builds on existing genetic programming methods.
The paper tackles the problem of automating CNN architecture design for image classification using Cartesian genetic programming, achieving competitive performance on CIFAR-10 compared to state-of-the-art models.
The convolutional neural network (CNN), which is one of the deep learning models, has seen much success in a variety of computer vision tasks. However, designing CNN architectures still requires expert knowledge and a lot of trial and error. In this paper, we attempt to automatically construct CNN architectures for an image classification task based on Cartesian genetic programming (CGP). In our method, we adopt highly functional modules, such as convolutional blocks and tensor concatenation, as the node functions in CGP. The CNN structure and connectivity represented by the CGP encoding method are optimized to maximize the validation accuracy. To evaluate the proposed method, we constructed a CNN architecture for the image classification task with the CIFAR-10 dataset. The experimental result shows that the proposed method can be used to automatically find the competitive CNN architecture compared with state-of-the-art models.