Investigating the Application of Transfer Learning Techniques in Cloud-Based AI Systems for Improved Performance and Reduced Training Time

  • Rishabh Rajesh Shanbhag Independent Researcher, USA
  • Siddhant Benadikar Independent Researcher, USA
  • Ugandhar Dasi Independent Researcher, USA
  • Nikhil Singla Independent Researcher, USA
  • Rajkumar Balasubramanian Independent Researcher, USA
Keywords: Transfer Learning, Cloud Computing, Artificial Intelligence, Machine Learning, Distributed Computing, Model Optimization, Fine-tuning, Domain Adaptation, Federated Learning, Performance Metrics

Abstract

This current research paper examines the adaptive technology solution approaches of transfer learning in a cloud environment for AI systems’ enhanced results and faster training periods. Concerning transfer learning methods, their application with cloud computing environments, and their effects on the efficiency of the AI model are the subject of the study. In this work, after reviewing the current literature and the state of the art of transfer learning and cloud-based AI, we discuss their integration’s prospects and opportunities for scalability, data privacy, and model generalization. The study sheds light on how transfer learning can go a long way in strengthening the efficiency of cloud AI, especially in facets such as speech and language processing, image identification, and speech recognition. The results of our study point out that it is possible to significantly improve the efficiency of model training and accuracy by applying transfer learning methodologies, thus opening opportunities for more dynamic AI solutions in the cloud context.

Published
2024-02-04
Issue
Volume 2024
Section
Regular Issue

Letters in High Energy Physics (LHEP) is an open access journal. The articles in LHEP are distributed according to the terms of the creative commons license CC-BY 4.0. Under the terms of this license, copyright is retained by the author while use, distribution and reproduction in any medium are permitted provided proper credit is given to original authors and sources.

Terms of Submission

By submitting an article for publication in LHEP, the submitting author asserts that:

1. The article presents original contributions by the author(s) which have not been published previously in a peer-reviewed medium and are not subject to copyright protection.

2. The co-authors of the article, if any, as well as any institution whose approval is required, agree to the publication of the article in LHEP.