Cartesian Genetic Programming Approach for Designing Convolutional Neural Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913544106147840 |
|---|---|
| author | Krzywda, Maciej Łukasik, Szymon H, Amir Gandomi |
| author_facet | Krzywda, Maciej Łukasik, Szymon H, Amir Gandomi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_00129 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cartesian Genetic Programming Approach for Designing Convolutional Neural Networks Krzywda, Maciej Łukasik, Szymon H, Amir Gandomi Neural and Evolutionary Computing Artificial Intelligence Machine Learning 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. |
| title | Cartesian Genetic Programming Approach for Designing Convolutional Neural Networks |
| topic | Neural and Evolutionary Computing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.00129 |