Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{180860,
        author = {Lekshmi M and Revathy A S and Libina Rose Sebastian},
        title = {From Transformers to TinyML: A Review of Emerging Trends in Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {3609-3612},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180860},
        abstract = {The evolution of deep learning has fundamentally altered the landscape of artificial intelligence (AI), empowering systems to extract and generalize from vast, complex datasets. In recent years, the field has surged forward, propelled by breakthroughs in model architectures, learning frameworks, and scalable deployment techniques. This review explores key advancements shaping the current state of deep learning, including the emergence of transformer architectures, the rise of self-supervised learning, innovations in building efficient models, the integration of multiple data modalities, and the growing focus on ethical and responsible AI development. By examining these trends, we identify critical challenges and highlight future research opportunities that are poised to define the next chapter of deep learning innovation.},
        keywords = {Deep learning, transformer architectures, self-supervised learning, model efficiency, multimodal systems, AI ethics, foundation models.},
        month = {June},
        }