Tim Brailsford's Outputs (2)

ResNet18 performance: Impact of network depth and image resolution on image classification (2024)
Presentation / Conference Contribution

This study explores aspects of using ResNet18 for the classification of biomedical images, using the 2D medical images from the MedMNIST library that is widely used for benchmarking. The number of layers within the ResNet18 was studied. The typically... Read More about ResNet18 performance: Impact of network depth and image resolution on image classification.

Examining neural networks through architectural variation analysis for image classification (2024)
Presentation / Conference Contribution

This paper presents a method for examining neural networks in image classification through architectural variation analysis. Small-scale experiments generate initial insights, and the configurations are further tested on entire datasets. The newly pr... Read More about Examining neural networks through architectural variation analysis for image classification.