Proposed Methods for Preventing Overfitting in Machine Learning  and Deep Learning

Vladimir Diukarev; Yaroslav Starukhin

doi:10.9734/ajrcos/2024/v17i10511

Research Article Open access CC BY 4.0

Proposed Methods for Preventing Overfitting in Machine Learning and Deep Learning

Vladimir Diukarev, Yaroslav Starukhin

Asian Journal of Research in Computer Science · pp. 85–94 · Published 9 Oct 2024

10.9734/ajrcos/2024/v17i10511

Abstract

The article discusses various approaches and methods to combat overfitting, which is a key problem in the field of artificial intelligence. Overfitting occurs when the model over-adapts to the training dataset, losing the ability to generalize to new data. The main causes and signs of overfitting are also discussed, including excessive complexity of models and limited data. The focus is on methods such as regularization, dropout, and the use of ensemble methods that can significantly reduce the risk of overfitting. These approaches are evaluated using examples from various fields of neural network applications, providing the reader with a comprehensive understanding of the problem and its solution methods.

Deep learning overfitting dropout regularization AI artificial intelligence

Cited by 19

AI-driven modelling and experimental analysis of oil concentration impact on mayonnaise rheology for innovative food design

Kadeejathul Kubra, S. Nambyaruveettil, Malaz Suliman · Journal of Food Engineering · 2025

LLM-Based Sentiment Analysis of RPG Genre Game Reviews on Steam

Erlangga Dewa Sakti, Mahendra Dwifebri Purbolaksono, Alfian Akbar Gozali · 2025 International Conference on Data Science and Its Applications (ICoDSA) · 2025

Enhancing deep learning models for predicting smoking Status using clinical data in patients with chronic obstructive pulmonary disease

Sehyun Cho, Hyeonseok Jin, Kyungbaek Kim · Digital Health · 2025

Research on Collaborative Filtering Algorithm of E-commerce Based on Flink

Haohao Zheng, Xiao-Nan Luo, Xiaoshu Zhu · International Conference on Intelligent Control and Information Processing · 2025

Showing 14 of 19 known citations — external sources report more than can currently be individually listed.

Risk of AI in Healthcare: A Comprehensive Literature Review and Study Framework — shares topic coverage
The Role of AI in Epidemiological Research: Applications, Benefits, and Risks in Modern Public Health — shares topic coverage
Infusing Intent and Its Management into Turing Machine: A Path to Cognitive Distributed Computing — shares topic coverage
Digital Technology: A Game Changer in Vegetable Cultivation — shares topic coverage
AI Tool for Sustainable Project Management Construction (SPMC) — shares topic coverage

Access this article

View at publisher

Cite this article

Vladimir Diukarev, Yaroslav Starukhin (2024). Proposed Methods for Preventing Overfitting in Machine Learning and Deep Learning. Asian Journal of Research in Computer Science , 85–94. https://doi.org/10.9734/ajrcos/2024/v17i10511

Affiliations

Vladimir Diukarev — Anti-Fraud Department, Sberbank, Moscow, Russian Federation.
Yaroslav Starukhin — McKinsey & Company, Boston, USA.

Metrics

14
Views: 0
Downloads: 19
Citations: 2
Outbound

Full metrics

Article metrics

Real usage data collected on this platform.

14

Page views

0

PDF downloads

2

Outbound clicks

19

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.