Article

Methods for Improving the Efficiency of Artificial Intelligence on Small Datasets: Alternative Algorithms and Transfer Learning

Otepbergenov Jetkerbay SakbergenovichNukus State Pedagogical Institute named after Ajiniyaz, Department of Digital Technologies, Informatics, and Robotics, Associate Professor. Doctor of Pedagogical Sciences (DSc), Uzbekistan

International Journal of Pedagogicsjournal2026

ABI

Abstract

Small datasets pose significant challenges for training artificial intelligence models. This article analyzes methods aimed at enhancing the generalization capabilities of models, reducing overfitting, and ensuring efficient use of resources. Specifically, transfer learning, meta-learning, Bayesian neural networks, and few-shot learning approaches are comparatively studied. The results indicate that transfer and hybrid methods are effective in increasing accuracy and reducing error on small datasets. The article also provides practical recommendations and directions for future research.

Topics

Domain Adaptation and Few-Shot Learning Machine Learning and Data Classification Machine Learning in Healthcare

Identifiers

DOI: 10.37547/ijp/volume06issue04-61

Citations and references

Cited by 00 references

Metrics — AkademScholar