Artificial General Intelligence
by T. Saravanan, P. Preethi, Sumaya Sanober, N. Thillaiarasu, S. Balamurugan
8Self-Supervised Learning Approaches for Enhancing the Adaptability of Artificial General Intelligence Models
R. Pushpalakshmi1*, G. Kalaiarasi2, C. P. Thamil Selvi3, Nithya C.4 and D. Satheesh Kumar5
1School of Computer Science and Engineering, VIT University, Vellore, India
2Department of Advanced Computer Science and Engineering, Vignans Foundation for Science, Technology and Research, Vadlamudi, Andhra Pradesh, India
3Department of Artificial Intelligence and Data Science, Rathinam Technical Campus, Coimbatore, Tamilnadu, India
4Department of Computer Science and Business Systems, Knowledge Institute of Technology, Salem, Tamilnadu, India
5Department of Artificial Intelligence and Machine Learning, Hindusthan College of Engineering and Technology, Coimbatore, Tamilnadu, India
Abstract
Artificial general intelligence (AGI) aims to replicate the intellectual flexibility and richness of the human mind for a wide range of tasks and settings. One of the principal bottlenecks in achieving this vision is the dependence of classic learning systems on large amounts of labeled data, restraining scalability, generalizability, and contextual awareness. Self-supervised learning (SSL) presents itself as a revolutionary approach where AGI systems learn meaningful representations from unlabeled data by creating their own supervisory signals. This work discusses how SSL methods can be systematically incorporated into AGI systems to make them more adaptable, better at abstraction, and more ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access