Молимо вас користите овај идентификатор за цитирање или овај линк до ове ставке:
https://scidar.kg.ac.rs/handle/123456789/21735
Назив: | Evolutionary approach for composing a thoroughly optimized ensemble of regression neural networks |
Аутори: | Krstic, Lazar Ivanović, Miloš Simic, Visnja Stojanović, Boban |
Часопис: | Egyptian Informatics Journal |
Датум издавања: | 2024 |
Сажетак: | The paper presents the GeNNsem (Genetic algorithm ANNs ensemble) software framework for the simultaneous optimization of individual neural networks and building their optimal ensemble. The proposed framework employs a genetic algorithm to search for suitable architectures and hyperparameters of the individual neural networks to maximize the weighted sum of accuracy and diversity in their predictions. The optimal ensemble consists of networks with low errors but diverse predictions, resulting in a more generalized model. The scalability of the proposed framework is ensured by utilizing micro-services and Kubernetes batching orchestration. GeNNsem has been evaluated on two regression benchmark problems and compared with related machine learning techniques. The proposed approach exhibited supremacy over other ensemble approaches and individual neural networks in all common regression modeling metrics. Real-world use-case experiments in the domain of hydro-informatics have further demonstrated the main advantages of GeNNsem: requires the least training sessions for individual models when optimizing an ensemble; networks in an ensemble are generally simple due to the regularization provided by a trivial initial population and custom genetic operators; execution times are reduced by two orders of magnitude as a result of parallelization. |
URI: | https://scidar.kg.ac.rs/handle/123456789/21735 |
Тип: | article |
DOI: | 10.1016/j.eij.2024.100581 |
ISSN: | 11108665 |
Налази се у колекцијама: | Faculty of Science, Kragujevac |
Датотеке у овој ставци:
Датотека | Опис | Величина | Формат | |
---|---|---|---|---|
GeNNsem_body_Egyptian_Informatics_Journal.pdf | 532.63 kB | Adobe PDF | Погледајте |
Ставке на SCIDAR-у су заштићене ауторским правима, са свим правима задржаним, осим ако није другачије назначено.