CCL

Összesen 2 találat.
#/oldal:
Részletezés:
Rendezés:

1.

001-es BibID:BIBFORM103625
035-os BibID:(WOS)000618845500006 (Scopus)85092677334
Első szerző:Beregi-Kovács Marcell (Alkalmazott matematikus)
Cím:Efficient Learning of Model Weights via Changing Features During Training / Marcell Beregi-Kovács, Ágnes Baran, András Hajdu
Dátum:2020
Megjegyzések:In this paper, we propose a machine learning model, which dynamically changes the features during training. Our main motivation is to update the model in a small content during the training process with replacing less descriptive features to new ones from a large pool. The main benefit is coming from the fact that opposite to the common practice we do not start training a new model from the scratch, but can keep the already learned weights. This procedure allows the scan of a large feature pool which together with keeping the complexity of the model leads to an increase of the model accuracy within the same training time. The efficiency of our approach is demonstrated in several classic machine learning scenarios including linear regression and neural network-based training. As a specific analysis towards signal processing, we have successfully tested our approach on the database MNIST for digit classification considering single pixel and pixel-pairs intensities as possible features.
Tárgyszavak:Természettudományok Matematika- és számítástudományok konferenciacikk
folyóiratcikk
machine learning
updating model weights
linear regression
neural networks
image classification
Megjelenés:2020 IEEE 24th International Conference on Intelligent Engineering Systems (INES). - 2020 (2020), p. 43-48. -
További szerzők:Baran Ágnes (1972-) (matematikus) Hajdu András (1973-) (matematikus, informatikus)
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:

2.

001-es BibID:BIBFORM116613
035-os BibID:(cikkazonosító)4730 (Scopus)85178934416
Első szerző:Harangi Balázs (programtervező matematikus)
Cím:Composing Diverse Ensembles of Convolutional Neural Networks by Penalization / Balazs Harangi, Agnes Baran, Marcell Beregi-Kovacs, Andras Hajdu
Dátum:2023
ISSN:2227-7390
Megjegyzések:Ensemble-based systems are well known to have the capacity to outperform individual approaches if the ensemble members are sufficiently accurate and diverse. This paper investigates how an efficient ensemble of deep convolutional neural networks (CNNs) can be created by forcing them to adjust their parameters during the training process to increase diversity in their decisions. As a new theoretical approach to reach this aim, we join the member neural architectures via a fully connected layer and insert a new correlation penalty term in the loss function to obstruct their similar operation. With this complementary term, we implement the standard guideline of ensemble creation to increase the members` diversity for CNNs in a more detailed and flexible way than similar existing techniques. As for applicability, we show that our approach can be efficiently used in various classification tasks. More specifically, we demonstrate its performance in challenging medical image analysis and natural image classification problems. Besides the theoretical considerations and foundations, our experimental findings suggest that the proposed technique is competitive. Namely, on the one hand, the classification rate of the ensemble trained in this way outperformed all the individual accuracies of the state-of-the-art member CNNs according to the standard error functions of these application domains. On the other hand, it is also validated that the ensemble members get more diverse and their accuracies are raised by adding the penalization term. Moreover, we performed a full comparative analysis, including other state-of-the-art ensemble-based approaches recommended for the same classification tasks. This comparative study also confirmed the superiority of our method, as it overcame the current solutions.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény külföldi lapban
folyóiratcikk
ensemble-based network
penalization
loss function
image classification
diversity
Megjelenés:Mathematics. - 11 : 23 (2023), p. 1-19. -
További szerzők:Baran Ágnes (1972-) (matematikus) Beregi-Kovács Marcell (1995-) (Alkalmazott matematikus) Hajdu András (1973-) (matematikus, informatikus)
Pályázati támogatás:ÚNKP-21-5-DE-485
Egyéb
Bolyai János Kutatási Ösztöndíj
MTA
Internet cím:Szerző által megadott URL
DOI
Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Rekordok letöltése1