Handwritten digit classification with convolutional neural network
Abstract
In this project, we develop a convolutional neural network (CNN) to classify handwritten digits from the MNIST dataset, a widely used benchmark in computer vision. Unlike traditional image-processing pipelines that rely on engineered features, CNNs automatically learn hierarchical representations directly from raw pixel data. Our model consists of two convolutional layers, max pooling, dropout for regularization, and two fully connected layers. Trained for five epochs using the Adadelta optimizer with learning rate decay, the network achieves a test accuracy of 98.92%. These results demonstrate that even a relatively small CNN can achieve strong performance on MNIST with minimal tuning.
Fields of Study & Subjects
Advanced Neural Network Applications
Handwritten Text Recognition Techniques
Computer Science and Engineering
Publication details
- Journal / source
- Advances in Engineering Innovation
- Volume
- 17
- Issue
- 3
- Pages
- 92–96
- Publication date
- 11 March 2026
- Language
- EN