Data Augmentation and Convolutional Network Architecture Influence on Distributed Learning

TL;DR

This paper investigates how different CNN architectures and data augmentation techniques affect accuracy and computational efficiency in distributed learning environments, providing insights for optimizing resource-intensive CNN deployment.

Contribution

It offers a comprehensive analysis of CNN architecture influence and data augmentation on distributed training performance, highlighting factors affecting efficiency and accuracy.

Findings

CNN architecture significantly impacts model accuracy.

Data augmentation improves training robustness.

Computational efficiency varies with architecture and augmentation strategies.

Abstract

Convolutional Neural Networks (CNNs) have proven to be highly effective in solving a broad spectrum of computer vision tasks, such as classification, identification, and segmentation. These methods can be deployed in both centralized and distributed environments, depending on the computational demands of the task. While much of the literature has focused on the explainability of CNNs, which is essential for building trust and confidence in their predictions, there remains a gap in understanding their impact on computational resources, particularly in distributed training contexts. In this study, we analyze how CNN architectures primarily influence model accuracy and investigate additional factors that affect computational efficiency in distributed systems. Our findings contribute valuable insights for optimizing the deployment of CNNs in resource-intensive scenarios, paving the way for further exploration of variables critical to distributed learning.