Skip to content
Research Article Open access CC BY 4.0

Dropout: An Effective Approach to Prevent Neural Networks from Overfitting

Shahwan Younis Ali, Hajar Maseeh

Asian Journal of Research in Computer Science · pp. 163–185 · Published 4 Feb 2025

10.9734/ajrcos/2025/v18i2569

Abstract

Overfitting remains a significant challenge in training neural networks, often leading to poor generalization on unseen data. Dropout has emerged as a powerful regularization technique to mitigate overfitting by randomly deactivating neurons during training, thereby preventing co-adaptation of features and encouraging diverse representations. This paper explores the theoretical foundations and practical implementations of dropout across various neural network architectures, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). Through empirical analysis on benchmark datasets such as CIFAR-10, MNIST, and others, dropout is shown to improve model robustness and accuracy significantly. The study also compares dropout with alternative regularization methods, such as weight constraints and batch normalization, highlighting its effectiveness in diverse scenarios. Despite its success, dropout's performance is influenced by hyperparameter tuning and dataset characteristics. The paper concludes by discussing limitations, such as computational overhead, and proposes directions for optimizing dropout for specific applications, including dynamic dropout rates and hybrid regularization techniques.

Overfitting dropout neural networks regularization Convolutional Neural Networks (CNNs) Recurrent Neural Networks (RNNs)

Cited by 31

AirQuaNet: A Convolutional Neural Network Model With Multi-Scale Feature Learning and Attention Mechanisms for Air Quality-Based Health Impact Prediction

Sreeni Chadalavada, Suleyman Yaman, Abdulkadir Sengur · IEEE Access · 2025

Analyzing CNN Performance for Image Processing Tasks

Manoj Kumar, Abdulkareem Saleh Ali Al Nahari · 2025 International Conference on Innovations in Intelligent Systems: Advancements in Computing, Communication, and Cybersecurity (ISAC3) · 2025

Offline Versus Real-Time Grasp Prediction Employing a Wearable High-Density Lightmyography Armband: On the Control of Prosthetic Hands

Bonnie Guan, Ricardo V. Godoy, Mojtaba Shahmohammadi · IEEE Access · 2025

Enhancing the performance of a deep convolutional neural network model for motor imagery classification using EEG channel-wise attention module

Vishnupriya R, Neethu Robinson, M Ramasubba Reddy · Medical Engineering & Physics · 2026

Data-Driven Soft Sensor for Optical Intensity Estimation in High-Power Plasma Source

Himanshu Tyagi, Manjunath Joshi, Mainak Bandyopadhyay · IEEE Sensors Journal · 2025

Robust UWB Positioning System Using Switching Tracking Filters With Estimated States-Based Non-Line-of-Sight Classifier

Miseon Han, Jeongtae Kim · IEEE Access · 2025

G2Dropout: gradient-guided dynamic dropout for efficient optimization of deep neural architectures through weights update analysis

Mohsen Heidari, Mohammad Hossein Moattar, Hamidreza Ghaffari · The Journal of Supercomputing · 2025

Lightweight Wavelet Convolutional U-Net for Seismic Phase Recognition

Jianxian Cai, Jingqi Ma, Yanxiong Wu · IEEE Access · 2026

Showing 8 of 31 known citations — external sources report more than can currently be individually listed.

Related research

Article metrics

Real usage data collected on this platform.

19

Page views

0

PDF downloads

2

Outbound clicks

31

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.