Detail publikace

TECHNIQUES FOR AVOIDING MODEL OVERFITTING ON SMALL DATASET

KRATOCHVÍLA, L.

Originální název

TECHNIQUES FOR AVOIDING MODEL OVERFITTING ON SMALL DATASET

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

KRATOCHVÍLA, L.

Vydáno

27. 4. 2021

Nakladatel

Vysoké učené Technické, Fakulta elektrotechniky a komunikačních technologií

Místo

Brno

ISBN

978-80-214-5942-7

Kniha

Proceedings I of the 27th Conference STUDENT EEICT 2021

Strany od

451

Strany do

456

Strany počet

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"
}