Cartesian Genetic Programming Approach for Designing Convolutional Neural Networks

TL;DR

This paper introduces a novel neural architecture search method using Cartesian genetic programming with mutation to automate CNN design, aiming to reduce manual effort and improve efficiency.

Contribution

It presents a pure genetic programming approach for CNN design, focusing on mutation-only evolution to automate neural architecture search.

Findings

Preliminary experiments show promising results.

The method simplifies CNN design process.

Potential for automating neural architecture search.

Abstract

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.