Data augmentation and generative machine learning on the cloud platform

Abstract

This paper aims to explore the image data augmentation application on the cloud platform utilizing state-of-the-art generative machine learning techniques. This paper further highlights these techniques’ significance in addressing the challenge of data generation and emphasizes the need for further research in this area. This research adopts an in-depth exploration approach to examine the burgeoning domain of generative machine learning techniques. It discusses the evolution of these techniques and their integration with cloud services powered by Graphical Processing Unit (GPU)-enabled computational engines. Practical experimentation involving Modified National Institute of Standards and Technology (MNIST) data is conducted to showcase the capabilities of generative models, with a focus on the core Generative Adversarial Network (GAN). The findings reveal the potential of generative machine learning techniques in generating new data images, as demonstrated through practical experimentation with MNIST data. It also highlights the ongoing evolution of these techniques and their challenges, particularly in terms of computational requirements and integration with cloud computing services. This research originally contributes to the existing literature by providing insights into recent advancements and challenges in GANs and their synergies with cloud computing. It presents results from experimentation and emphasizes the importance of cost-effective development environments for implementing generative machine learning techniques.