The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)
31 Downloads (Pure)

Abstract

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.

Original languageEnglish
Pages (from-to)312-315
Number of pages4
JournalICT Express
Volume6
Issue number4
Early online date5 May 2020
DOIs
Publication statusPublished - Dec 2020

Keywords

  • Batch size
  • Convolutional neural networks
  • Deep learning
  • Image classification
  • Medical images

Fingerprint Dive into the research topics of 'The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset'. Together they form a unique fingerprint.

Cite this