Transfer Learning: Bridging Domains in Machine Learning
Keywords:
Transfer learning, Information technology, Algorithm, Artificial Neural NetworksAbstract
Transfer learning uses pre-trained information from a large-scale dataset (like ImageNet) to a target task with sparsely labeled data. This strategy improves learning performance and generalization by enabling models to draw on the learnt representations and efficiently apply information to new challenges. Transfer learning has been used extensively in many fields, and its use is growing as computer networks, information technology, and related businesses grow quickly. Transfer learning offers excellent growth chances and tremendous development potential. The TL approach has a number of benefits, especially in domains that use images. These benefits include minimizing the scarcity of data, avoiding overfitting, quickening the pace of convergence, enhancing the quality of extracted features and data reuse, facilitating simulation training, cutting down on training time, and enhancing generalization ability.
References
[1] A. H. Ali, M. G. Yaseen, M. Aljanabi, and S. A. Abed, "Transfer Learning : A New Promising Techniques," no. February, 2023,
https://doi.org/10.58496/MJBD/2023/004
[2] H. Tercan, A. Guajardo, J. Heinisch, T. Thiele, C. Hopmann, and T. Meisen, "Transfer-Learning : Bridging the Gap between Real and Simulation Data for Machine Learning in Injection Molding," Procedia CIRP, vol. 72, no. March, pp. 185-190, 2018,
https://doi.org/10.1016/j.procir.2018.03.087
[3] M. Iman, H. R. Arabnia, and K. Rasheed, "A Review of Deep Transfer Learning and Recent Advancements," pp. 1-14, 2023.
https://doi.org/10.3390/technologies11020040
[4] Z. Zhao, L. Alzubaidi, J. Zhang, Y. Duan, and Y. Gu, "A comparison review of transfer learning and self-supervised learning : Definitions , applications , advantages and limitations," Expert Syst. Appl., vol. 242, no. June 2023, p. 122807, 2024,
https://doi.org/10.1016/j.eswa.2023.122807
[5] X. Wu, J. H. Manton, U. Aickelin, and J. Zhu, "On the Generalization for Transfer Learning : An Information-Theoretic Analysis," 2024.
https://doi.org/10.1109/TIT.2024.3441574
[6] G. Baruffa, A. Pieressa, M. Sorgato, and G. Lucchetta, "Transfer Learning-Based Artificial Neural Network for Predicting Weld Line Occurrence through Process Simulations and Molding Trials," 2024.
https://doi.org/10.3390/jmmp8030098
[7] J. Gupta, S. Pathak, and G. Kumar, "Deep Learning (CNN) and Transfer Learning: A Review," 2022,
https://doi.org/10.1088/1742-6596/2273/1/012029
[8] F. Yu, X. Xiu, and Y. Li, "A Survey on Deep Transfer Learning and Beyond," pp. 1-27, 2022.
https://doi.org/10.3390/math10193619
[9] A. Hosna, E. Merry, J. Gyalmo, Z. Alom, Z. Aung, and M. A. Azim, "Transfer learning : a friendly introduction," J. Big Data, 2022,
https://doi.org/10.1186/s40537-022-00652-w
[10] T. Phung et al., "On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources," no. NeurIPS, pp. 1-31, 2021.
[11] Y. Zhou, X. Zhang, Y. Wang, and B. Zhang, "Transfer learning and its application research," 2021,
https://doi.org/10.1088/1742-6596/1920/1/012058
[12] F. ZHUANG et al., "A Comprehensive Survey on Transfer Learning," 2020.
