Cartesian Genetic Programming Approach for Designing Convolutional Neural Networks
This work addresses the time-consuming and error-prone manual design of CNN architectures for machine learning practitioners, offering an automated alternative.
This paper explores the use of Cartesian Genetic Programming (CGP) for Neural Architecture Search (NAS) to design Convolutional Neural Networks (CNNs). The approach uses only mutation as a genetic operation and shows promising preliminary results.
The present study covers an approach to neural architecture search (NAS) using Cartesian genetic programming (CGP) for the design and optimization of Convolutional Neural Networks (CNNs). In designing artificial neural networks, one crucial aspect of the innovative approach is suggesting a novel neural architecture. Currently used architectures have mostly been developed manually by human experts, which is a time-consuming and error-prone process. In this work, we use pure Genetic Programming Approach to design CNNs, which employs only one genetic operation, i.e., mutation. In the course of preliminary experiments, our methodology yields promising results.