The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset
Year: 2020
Type: article
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.
Source: ICT Express
Authors: Ibrahem Kandel, Mauro Castelli
Institution: Universidade Nova de Lisboa
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,500
Awards: Digitalization as Driving Force for Sustainability of Individuals, Organizations, and Society, Ciência de Dados e o Sobre-Endividamento: Uso de Algoritmos de Inteligência Artificial no Consumo de Crédito e Conciliação de Endividamento em Portugal, Deteção de padrões de adição em jogo online, G7793961641
OpenAlex ID: W3021970402
