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{155681,
        author = {Aditya Paprunia and Jyoti Malhotra},
        title = {Inductive and Transductive Transfer learning : COMODEL},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {9},
        number = {1},
        pages = {1524-1531},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=155681},
        abstract = {Transfer Learning is a commonly used method in deep learning to train neural networks from a previously trained model. It focuses on using knowledge gained while solving one problem to solve a similar problem without explicitly developing a solution for the new problem. Similarly, previously trained models were created for a specific goal, but their learnings can be applied to other tasks as well. The new model uses the pre-trained model as the starting point for the new task. It extracts meaningful features from previous models and uses them for the current problem. In this research paper we compare the performance of the different pre-trained models; as per their accuracy with training data and validation data to get an idea of which model is best suited to give better results when transfer learning is used.},
        keywords = {},
        month = {},
        }