Please use this identifier to cite or link to this item:
https://scidar.kg.ac.rs/handle/123456789/21735
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Krstic, Lazar | - |
dc.contributor.author | Ivanović, Miloš | - |
dc.contributor.author | Simic, Visnja | - |
dc.contributor.author | Stojanović, Boban | - |
dc.date.accessioned | 2024-12-06T07:39:36Z | - |
dc.date.available | 2024-12-06T07:39:36Z | - |
dc.date.issued | 2024 | - |
dc.identifier.issn | 11108665 | en_US |
dc.identifier.uri | https://scidar.kg.ac.rs/handle/123456789/21735 | - |
dc.description.abstract | 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. | en_US |
dc.description.sponsorship | This paper is funded through the EIT’s HEI Initiative DEEPTECH-2M project, supported by EIT Digital and coordinated by EIT RawMaterials, funded by the European Union. | en_US |
dc.language.iso | en_US | en_US |
dc.relation.ispartof | Egyptian Informatics Journal | en_US |
dc.subject | Ensemble modeling | en_US |
dc.subject | Regression | en_US |
dc.subject | ANN | en_US |
dc.subject | Genetic algorithm | en_US |
dc.subject | Distributed computing | en_US |
dc.title | Evolutionary approach for composing a thoroughly optimized ensemble of regression neural networks | en_US |
dc.type | article | en_US |
dc.description.version | Author's version | en_US |
dc.identifier.doi | 10.1016/j.eij.2024.100581 | en_US |
dc.type.version | WorkingVersion | en_US |
Appears in Collections: | Faculty of Science, Kragujevac |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
GeNNsem_body_Egyptian_Informatics_Journal.pdf | 532.63 kB | Adobe PDF | View/Open |
Items in SCIDAR are protected by copyright, with all rights reserved, unless otherwise indicated.