Publication detail

TECHNIQUES FOR AVOIDING MODEL OVERFITTING ON SMALL DATASET

KRATOCHVÍLA, L.

Original Title

TECHNIQUES FOR AVOIDING MODEL OVERFITTING ON SMALL DATASET

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

Building a deep learning model based on small dataset is difficult, even impossible. To avoiding 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 simple CNN 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.

Keywords

Deep Learning; Dataset size; Overfitting; Data Augmentation; Regularization; Image Classification; Batch Normalization; Data Normalization

Authors

KRATOCHVÍLA, L.

Released

27. 4. 2021

Publisher

Vysoké učené Technické, Fakulta elektrotechniky a komunikačních technologií

Location

Brno

ISBN

978-80-214-5942-7

Book

Proceedings I of the 27th Conference STUDENT EEICT 2021

Pages from

451

Pages to

456

Pages count

5

BibTex

@inproceedings{BUT171161,
  author="Lukáš {Kratochvíla}",
  title="TECHNIQUES FOR AVOIDING MODEL OVERFITTING ON SMALL DATASET",
  booktitle="Proceedings I of the 27th Conference STUDENT EEICT 2021",
  year="2021",
  pages="451--456",
  publisher="Vysoké učené Technické, Fakulta elektrotechniky a komunikačních technologií",
  address="Brno",
  isbn="978-80-214-5942-7"
}