Enhanced Convolutional Neural Networks for MNIST Digit Recognition | ||||
| International Integrated Intelligent Systems | ||||
| Volume 1, Issue 2, June 2024 PDF (360.88 K) | ||||
| DOI: 10.21608/iiis.2024.357780 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
| Ahmed Gamal* 1; Mohammed El Saeed* 2; Mohanad Deif3; Rania Elgohary3 | ||||
| 1Faculty of Engineering Cairo University, Cairo, Egypt | ||||
| 2Faculty of Engineering Cairo University Cairo, Egypt | ||||
| 3Department of Artificial intelligence , College of Information Technology, Misr University for Science & Technology (MUST), 6th of October City 12566 , Egypt | ||||
| Abstract | ||||
| This study addresses the ongoing pursuit of achieving optimal performance in digit recognition tasks, focusing on the widely studied MNIST dataset. Our motivation stems from the challenge of accurately classifying the remaining 1% of images, despite the relatively high 99% accuracy achieved by existing models. In this work, we present a simplified approach to convolutional neural network (CNN) architecture, aiming to streamline model complexity while maintaining or even enhancing performance. Unlike previous approaches, our methodology involves utilizing only two CNN layers with fewer filters, resulting in a reduction in model parameters and learning time. Through rigorous experimentation and evaluation, we demonstrate that our streamlined CNN architecture yields competitive results. Our findings underscore the importance of exploring alternative model architectures and optimization techniques to achieve state-of-the-art performance in digit recognition tasks. | ||||
| Keywords | ||||
| Convolutional Neural Networks; MNIST; Digit Recognition | ||||
|
Statistics Article View: 115 PDF Download: 237 |
||||
