Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-22213
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Michelucci, Umberto | - |
dc.contributor.author | Venturini, Francesca | - |
dc.date.accessioned | 2021-04-01T07:08:11Z | - |
dc.date.available | 2021-04-01T07:08:11Z | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 2504-4990 | de_CH |
dc.identifier.uri | https://digitalcollection.zhaw.ch/handle/11475/22213 | - |
dc.description.abstract | Neural networks present characteristics where the results are strongly dependent on the training data, the weight initialisation, and the hyperparameters chosen. The determination of the distribution of a statistical estimator, as the Mean Squared Error (MSE) or the accuracy, is fundamental to evaluate the performance of a neural network model (NNM). For many machine learning models, as linear regression, it is possible to analytically obtain information as variance or confidence intervals on the results. Neural networks present the difficulty of not being analytically tractable due to their complexity. Therefore, it is impossible to easily estimate distributions of statistical estimators. When estimating the global performance of an NNM by estimating the MSE in a regression problem, for example, it is important to know the variance of the MSE. Bootstrap is one of the most important resampling techniques to estimate averages and variances, between other properties, of statistical estimators. In this tutorial, the application of resampling techniques (including bootstrap) to the evaluation of neural networks’ performance is explained from both a theoretical and practical point of view. The pseudo-code of the algorithms is provided to facilitate their implementation. Computational aspects, as the training time, are discussed, since resampling techniques always require simulations to be run many thousands of times and, therefore, are computationally intensive. A specific version of the bootstrap algorithm is presented that allows the estimation of the distribution of a statistical estimator when dealing with an NNM in a computationally effective way. Finally, algorithms are compared on both synthetically generated and real data to demonstrate their performance. | de_CH |
dc.language.iso | en | de_CH |
dc.publisher | MDPI | de_CH |
dc.relation.ispartof | Machine Learning and Knowledge Extraction | de_CH |
dc.rights | http://creativecommons.org/licenses/by/4.0/ | de_CH |
dc.subject | Neural network | de_CH |
dc.subject | Machine learning | de_CH |
dc.subject | Bootstrap | de_CH |
dc.subject | Resampling | de_CH |
dc.subject | Algorithm | de_CH |
dc.subject.ddc | 006: Spezielle Computerverfahren | de_CH |
dc.title | Estimating neural network’s performance with bootstrap : a tutorial | de_CH |
dc.type | Beitrag in wissenschaftlicher Zeitschrift | de_CH |
dcterms.type | Text | de_CH |
zhaw.departement | School of Engineering | de_CH |
zhaw.organisationalunit | Institut für Angewandte Mathematik und Physik (IAMP) | de_CH |
dc.identifier.doi | 10.3390/make3020018 | de_CH |
dc.identifier.doi | 10.21256/zhaw-22213 | - |
zhaw.funding.eu | No | de_CH |
zhaw.issue | 2 | de_CH |
zhaw.originated.zhaw | Yes | de_CH |
zhaw.pages.end | 373 | de_CH |
zhaw.pages.start | 357 | de_CH |
zhaw.publication.status | publishedVersion | de_CH |
zhaw.volume | 3 | de_CH |
zhaw.publication.review | Peer review (Publikation) | de_CH |
zhaw.author.additional | No | de_CH |
zhaw.display.portrait | Yes | de_CH |
Appears in collections: | Publikationen School of Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2021_Michelucci-Venturini_Neural-network-performance-bootstrap.pdf | 755.58 kB | Adobe PDF | View/Open |
Show simple item record
Michelucci, U., & Venturini, F. (2021). Estimating neural network’s performance with bootstrap : a tutorial. Machine Learning and Knowledge Extraction, 3(2), 357–373. https://doi.org/10.3390/make3020018
Michelucci, U. and Venturini, F. (2021) ‘Estimating neural network’s performance with bootstrap : a tutorial’, Machine Learning and Knowledge Extraction, 3(2), pp. 357–373. Available at: https://doi.org/10.3390/make3020018.
U. Michelucci and F. Venturini, “Estimating neural network’s performance with bootstrap : a tutorial,” Machine Learning and Knowledge Extraction, vol. 3, no. 2, pp. 357–373, 2021, doi: 10.3390/make3020018.
MICHELUCCI, Umberto und Francesca VENTURINI, 2021. Estimating neural network’s performance with bootstrap : a tutorial. Machine Learning and Knowledge Extraction. 2021. Bd. 3, Nr. 2, S. 357–373. DOI 10.3390/make3020018
Michelucci, Umberto, and Francesca Venturini. 2021. “Estimating Neural Network’s Performance with Bootstrap : A Tutorial.” Machine Learning and Knowledge Extraction 3 (2): 357–73. https://doi.org/10.3390/make3020018.
Michelucci, Umberto, and Francesca Venturini. “Estimating Neural Network’s Performance with Bootstrap : A Tutorial.” Machine Learning and Knowledge Extraction, vol. 3, no. 2, 2021, pp. 357–73, https://doi.org/10.3390/make3020018.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.