Self-Supervised Learning in AI: Transforming data efficiency and model generalization in machine learning

Sharmin Nahar 1, *, Md Mostafizur Rahman 2, Md Mostafijur Rahman 3, Md Mashfiquer Rahman 4, Md Shafiq Ullah 5 and Mohammad Shahadat Hossain 4

1 Department of Applied Physics, Electronics & Communication Engineering, University of Dhaka.
2 Department of Computer Science & Engineering, Daffodil International University Dhaka Bangladesh.
3 Department of Computer Science & Engineering, Rajshahi University of Engineering & Technology (RUET), Bangladesh.
4 Department of Computer Science, American International University-Bangladesh.
5 Department of Computer Science, Maharishi International University, Iowa, USA.
 
Research Article
World Journal of Advanced Engineering Technology and Sciences, 2023, 10(01), 222-234
Article DOI: 10.30574/wjaets.2023.10.1.0279
Publication history: 
Received on 02 September 2023; revised on 22 October 2023; accepted on 25 October 2023
 
Abstract: 
Self-supervised learning (SSL) represents a revolutionary AI paradigm which lets machines acquire significant data representations directly from unlabeled information through unsupervised learning approaches. SSL uses contrastive learning and masked data modeling and predictive learning approaches to optimize data efficiency thereby improving model generalization between multiple domains. This paper evaluates the core concepts of SSL alongside its superiority to supervised and unsupervised learning and its usage in different fields such as NLP, computer vision, speech recognition, healthcare, finance and robotics. The paper focuses on analysis of essential techniques and architectures which include SimCLR, MoCo, BERT, MAE, BYOL and approaches combining SSL with reinforcement learning and weak supervision methods. The research analyzes SSL's current challenges including operational expenses and representation degeneration as well as the assessment obstructions while proposing future uses for the method in mixed-data learning and minimal-resource contexts and artificial general intelligence (AGI). The adoption of SSL in real-world AI applications depends on effectively dealing with ethical matters that include bias issues and responsible AI practices and fairness assurance.
 
Keywords: 
Self-Supervised Learning; Data Efficiency; Model Generalization; Contrastive Learning; Masked Data Modeling; Predictive Learning; Reinforcement Learning
 
Full text article in PDF: 

Click here

 
Copyright information: 
Copyright © 2023 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0