Year: 2024
Type: article
Abstract: In-depth analysis of AutoML (Automated Machine Learning) tools in the context of automated deep learning, a rapidly evolving field aimed at simplifying and optimizing the development of deep learning models. AutoML tools automate various stages of the machine learning pipeline, including data preprocessing, feature selection, model selection, hyperparameter tuning, and model evaluation, making them accessible to non-experts and enhancing productivity for experts. The article reviews prominent AutoML tools, examining their methodologies, strengths, limitations, and performance across different tasks. Through comparative studies and practical applications, the effectiveness of these tools in producing robust and efficient deep learning models is evaluated. Additionally, the article explores emerging trends and future directions in the integration of AutoML with deep learning, highlighting the potential for these tools to revolutionize machine learning workflows and democratize access to advanced AI technologies.
DOI: 10.63995/fxpc8243
Authors: Liam Connor, Rebecca Kelly, Saoirse Murphy, Eoghan McCarthy, Edward Murray
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4410979007
