The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset
Kandel, Ibrahem (Author), Castelli, Mauro (Author)

.pdfPDF - Presentation file, Download (578,49 KB)

Many hyperparameters have to be tuned to have a robust convolutional neural network that will be able to accurately classify images. One of the most important hyperparameters is the batch size, which is the number of images used to train a single forward and backward pass. In this study, the effect of batch size on the performance of convolutional neural networks and the impact of learning rates will be studied for image classification, specifically for medical images. To train the network faster, a VGG16 network with ImageNet weights was used in this experiment. Our results concluded that a higher batch size does not usually achieve high accuracy, and the learning rate and the optimizer used will have a significant impact as well. Lowering the learning rate and decreasing the batch size will allow the network to train better, especially in the case of fine-tuning.

Work type:Article (dk_c)
Tipology:1.01 - Original Scientific Article
Organization:EF - Faculty of Economics
Number of pages:str. 312-315
Numbering:Vol. 6, iss. 4
ISSN on article:2405-9595
DOI:10.1016/j.icte.2020.04.010 Link is opened in a new window
COBISS.SI-ID:38422787 Link is opened in a new window
License:CC BY-NC-ND 4.0
This work is available under this license: Creative Commons Attribution Non-Commercial No Derivatives 4.0 International
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
AddThis uses cookies that require your consent. Edit consent...

Record is a part of a journal

Title:ICT express
COBISS.SI-ID:526132505 This link opens in a new window

Document is financed by a project

Funder:ARRS - Agencija za raziskovalno dejavnost Republike Slovenije (ARRS)
Project no.:P5-0410
Name:Digitalizacija kot gonilo trajnostnega razvoja posameznika, organizacij in družbe

Funder:FCT - Fundação para a Ciência e a Tecnologia, I.P.
Project no.:DSAIPA/DS/0022/2018

Funder:FCT - Fundação para a Ciência e a Tecnologia, I.P.
Project no.:DSAIPA/DS/0113/2019

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:


Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
There are no comments!