Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1280812

Neuroevolution for the Sustainable Evolution of Neural Networks


Otović, Erik; Lerga, Jonatan; Kalafatović, Daniela; Mauša, Goran
Neuroevolution for the Sustainable Evolution of Neural Networks // Proceedings of MIPRO 2023 - 46th ICT and Electronics Convention / Karolj Skala (ur.).
Opatija, 2023. str. 1045-1051 doi:10.23919/MIPRO57284.2023.10159943 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 1280812 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Neuroevolution for the Sustainable Evolution of Neural Networks

Autori
Otović, Erik ; Lerga, Jonatan ; Kalafatović, Daniela ; Mauša, Goran

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of MIPRO 2023 - 46th ICT and Electronics Convention / Karolj Skala - Opatija, 2023, 1045-1051

Skup
MIPRO 2023 - 46th ICT and Electronics Convention

Mjesto i datum
Opatija, Hrvatska, 22.05.2023. - 26.06.2023

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Machine Learning ; Neuroevolution ; Neural Networks ; Genetic Algorithm ; Sustainability ; Classification

Sažetak
The predictive performance of a neural network depends on its weights and architecture. Optimizers based on gradient descent are most commonly used to optimize the weights, and grid search is utilized to find the most suitable architecture from the list of predefined architectures. On the other hand, neuroevolution offers a solution for the simultaneous growth of neural network architecture and the evolution of its weights. Thus, it is not limited by the user- defined list of possible architectures and can find configurations optimal for a specific task. Both approaches can be effectively parallelized and take advantage of modern multi-process systems. In this research, we compare neuroevolution and backpropagation in terms of the time consumed by the algorithm, the predictive performance of the neural network, and the complexity of the neural network. The total time for each algorithm is measured along with the times for each section of the algorithm and the time spent on synchronization due to the multi- process setting. The neural networks are compared by their predictive performance in terms of Matthews correlation coefficient score and their complexity as the number of nodes and connections. The case study is based on two synthetic and two real-world datasets for classification tasks.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Biotehnologija u biomedicini (prirodno područje, biomedicina i zdravstvo, biotehničko područje)



POVEZANOST RADA


Ustanove:
Tehnički fakultet, Rijeka,
Sveučilište u Rijeci - Odjel za biotehnologiju

Profili:

Avatar Url Goran Mauša (autor)

Avatar Url Erik Otović (autor)

Avatar Url Daniela Kalafatović (autor)

Avatar Url Jonatan Lerga (autor)

Poveznice na cjeloviti tekst rada:

doi ieeexplore.ieee.org

Citiraj ovu publikaciju:

Otović, Erik; Lerga, Jonatan; Kalafatović, Daniela; Mauša, Goran
Neuroevolution for the Sustainable Evolution of Neural Networks // Proceedings of MIPRO 2023 - 46th ICT and Electronics Convention / Karolj Skala (ur.).
Opatija, 2023. str. 1045-1051 doi:10.23919/MIPRO57284.2023.10159943 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Otović, E., Lerga, J., Kalafatović, D. & Mauša, G. (2023) Neuroevolution for the Sustainable Evolution of Neural Networks. U: Karolj Skala (ur.)Proceedings of MIPRO 2023 - 46th ICT and Electronics Convention doi:10.23919/MIPRO57284.2023.10159943.
@article{article, author = {Otovi\'{c}, Erik and Lerga, Jonatan and Kalafatovi\'{c}, Daniela and Mau\v{s}a, Goran}, year = {2023}, pages = {1045-1051}, DOI = {10.23919/MIPRO57284.2023.10159943}, keywords = {Machine Learning, Neuroevolution, Neural Networks, Genetic Algorithm, Sustainability, Classification}, doi = {10.23919/MIPRO57284.2023.10159943}, title = {Neuroevolution for the Sustainable Evolution of Neural Networks}, keyword = {Machine Learning, Neuroevolution, Neural Networks, Genetic Algorithm, Sustainability, Classification}, publisherplace = {Opatija, Hrvatska} }
@article{article, author = {Otovi\'{c}, Erik and Lerga, Jonatan and Kalafatovi\'{c}, Daniela and Mau\v{s}a, Goran}, year = {2023}, pages = {1045-1051}, DOI = {10.23919/MIPRO57284.2023.10159943}, keywords = {Machine Learning, Neuroevolution, Neural Networks, Genetic Algorithm, Sustainability, Classification}, doi = {10.23919/MIPRO57284.2023.10159943}, title = {Neuroevolution for the Sustainable Evolution of Neural Networks}, keyword = {Machine Learning, Neuroevolution, Neural Networks, Genetic Algorithm, Sustainability, Classification}, publisherplace = {Opatija, Hrvatska} }

Citati:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font