AUTO: supervised learning with full model search and global optimisation

The AUTO algorithm is presented to incrementally build models and solve supervised learning problems. AUTO uses traditional derivative-free optimisation, like genetic algorithms, to search the problem space of arbitrary functions. With reinforcement learning, AUTO learns actions to guide its search...

Full description

Saved in:
Bibliographic Details
Published inJournal of experimental & theoretical artificial intelligence Vol. 36; no. 8; pp. 1619 - 1630
Main Authors Lovinger, Justin, Valova, Iren
Format Journal Article
LanguageEnglish
Published Abingdon Taylor & Francis 16.11.2024
Taylor & Francis Ltd
Subjects
Genetic algorithms
genetic programming
Global optimization
Machine learning
machine programming
Mathematical optimization
Multilayer perceptrons
Performance enhancement
Search process
Supervised learning
Online AccessGet full text
ISSN0952-813X
1362-3079
DOI10.1080/0952813X.2023.2165717

Cover

More Information
Summary:The AUTO algorithm is presented to incrementally build models and solve supervised learning problems. AUTO uses traditional derivative-free optimisation, like genetic algorithms, to search the problem space of arbitrary functions. With reinforcement learning, AUTO learns actions to guide its search process and gradually improve performance. A comparative analysis is presented exploring supervised learning performance and interpretability of AUTO models. Results indicate AUTO outperforms genetic programming and rivals multilayer perceptrons. AUTO automatically builds models to closely match datasets without the limited search space of traditional supervised learning. With enough time and computational resources, AUTO can generate any function.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0952-813X
1362-3079
DOI:10.1080/0952813X.2023.2165717