A Custom CNN Architecture for Image Recognition using CIFAR‑10

Authors

  • Hayden Bin Nor Azman Faculty of Innovation and Technology, Taylor’s University, Selangor, Malaysia
  • Abdul Salam Shah Faculty of Innovation and Technology, Taylor’s University, Selangor, Malaysia

DOI:

https://doi.org/10.33150/JITDETS-8.2.6

Keywords:

CIFAR‑10, Convolutional Neural Networks (CNNs), Rectified linear units

Abstract

Deep Learning algorithms have remained prominent in image classification across various domains. CNNs have modernized the process, enabling automated classification in new fields. Traditional models suffer from lower accuracy largely due to manual feature extraction. To address challenges in modern algorithms, this paper proposes a CNN‑based model for the multi‑class problem using the CIFAR‑10 dataset. The hyperparameters have been carefully selected to achieve higher accuracy while avoiding overfitting. Data augmentation and dropout layers contributed to achieving 85.49% accuracy

Downloads

Published

2024-12-26

How to Cite

[1]
Hayden Bin Nor Azman and Abdul Salam Shah, “A Custom CNN Architecture for Image Recognition using CIFAR‑10”, J. ICT des. eng. technol. sci., vol. 8, no. 2, p. 32‑36, Dec. 2024.

Issue

Volume 8, Issue 2

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.