Techniques For Avoiding Model Overfitting On Small Dataset
| but.event.date | 27.04.2021 | cs |
| but.event.title | STUDENT EEICT 2021 | cs |
| dc.contributor.author | Kratochvila, Lukas | |
| dc.date.accessioned | 2021-07-21T07:07:00Z | |
| dc.date.available | 2021-07-21T07:07:00Z | |
| dc.date.issued | 2021 | cs |
| dc.description.abstract | Building a deep learning model based on small dataset is difficult, even impossible. Toavoiding overfitting, we must constrain model, which we train. Techniques as data augmentation,regularization or data normalization could be crucial. We have created a benchmark with a simpleCNN image classifier in order to find the best techniques. As a result, we compare different types ofdata augmentation and weights regularization and data normalization on a small dataset. | en |
| dc.format | text | cs |
| dc.format.extent | 451-456 | cs |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.citation | Proceedings I of the 27st Conference STUDENT EEICT 2021: General papers. s. 451-456. ISBN 978-80-214-5942-7 | cs |
| dc.identifier.isbn | 978-80-214-5942-7 | |
| dc.identifier.uri | http://hdl.handle.net/11012/200799 | |
| dc.language.iso | en | cs |
| dc.publisher | Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií | cs |
| dc.relation.ispartof | Proceedings I of the 27st Conference STUDENT EEICT 2021: General papers | en |
| dc.relation.uri | https://conf.feec.vutbr.cz/eeict/index/pages/view/ke_stazeni | cs |
| dc.rights | © Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií | cs |
| dc.rights.access | openAccess | en |
| dc.subject | Deep Learning | en |
| dc.subject | Dataset size | en |
| dc.subject | Overfitting | en |
| dc.subject | Data Augmentation | en |
| dc.subject | Regularization | en |
| dc.subject | ImageClassification | en |
| dc.subject | Batch Normalization | en |
| dc.subject | Data Normalization | en |
| dc.title | Techniques For Avoiding Model Overfitting On Small Dataset | en |
| dc.type.driver | conferenceObject | en |
| dc.type.status | Peer-reviewed | en |
| dc.type.version | publishedVersion | en |
| eprints.affiliatedInstitution.department | Fakulta elektrotechniky a komunikačních technologií | cs |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- 451_eeict-2021_1.pdf
- Size:
- 578.34 KB
- Format:
- Adobe Portable Document Format
- Description: